zobrx

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds value by disclosing that it returns 'citeable product records (document text)' and ties the id format to `product:<id>`, which goes beyond the annotations. It doesn't mention error cases or rate limits, but the read-only, non-destructive nature is well-covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loaded with the action ('Fetch the full detail'), and every sentence adds meaningful information. There is no fluff or repetition; it efficiently communicates the tool's purpose, input format, and output nature.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a simple one-parameter, read-only tool with an output schema present. The description sufficiently explains the workflow context (after `search`, for deep-research), the id format, and the return value ('citeable product records'). It is complete for the tool's complexity and relies appropriately on the output schema for return details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides a complete description of the only parameter `id`, including an example ('product:665f...'). The tool description essentially repeats this information, adding no new parameter-specific semantics. With schema coverage at 100%, the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (fetch full detail), the resource (a result returned by `search`), and the scope (by id). It explicitly distinguishes this from sibling tools like `search` by defining it as a follow-up, and even specifies the return type ('citeable product records'). This is a specific verb+resource+scope formulation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context: use this tool after `search` to get full detail of a returned result id. It doesn't explicitly list alternatives or when-not-to-use scenarios, but the prerequisite of having a search result id is clear. The mention of 'deep-research workflows' adds contextual guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds useful content details but does not disclose any additional behavioral traits such as auth requirements, data freshness, or response scope limitations. With annotations present, this is adequate but not enriched.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that lists all key data points without redundancy or filler. Every word adds value, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter read-only getter with an output schema and read-only annotations, the description fully covers what the agent needs to know: the resource and its key fields. There are no missing prerequisites, side effects, or usage constraints that would require additional context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description appropriately explains what the returned profile contains, and since no parameters exist, no parameter-specific guidance is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource as the workspace profile and enumerates specific contents (user details, corporate/tenant profile fields), making its purpose unambiguous. It lacks an explicit verb in the description, but the title 'Get account profile' supplies it, and the unique resource distinguishes it from sibling get_* tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus any alternatives. No context is given about scenarios, prerequisites, or why this tool would be preferred over similar profile-related tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, covering the safety profile. The description adds value by specifying the exact fields returned, which sets expectations about the output contents. No additional behavioral traits (rate limits, auth, side effects) are needed for this simple read-only tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence formatted as a concise list. Every word earns its place, with no filler or redundancy. It immediately identifies the resource and enumerates the key output components in a structured way.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (zero parameters, output schema present, annotations covering safety), the description is complete. It fully conveys what the agent can expect to receive. The sibling context of numerous get_* tools does not create ambiguity because the resource name 'AI wallet' is specific and sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and the input schema is empty with all properties absent. Per the rubric, a baseline of 4 applies since there are no parameters to describe. The description naturally contains no parameter information, which is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns AI wallet data, enumerating five specific data points: balance, month-to-date spend, monthly cap, auto-recharge status, and last top-up. This distinguishes it from sibling tools by naming the exact resource and content, making it unambiguous which get_* tool to select.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when an agent needs AI wallet financial information, but it does not explicitly state when to use this tool versus alternatives or provide any exclusionary guidance. There is no mention of alternative tools for related budgeting queries, so the guidance remains implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds the window scope and metric breakdown but does not disclose additional behavioral traits (e.g., pagination, timezone, rate limits). Given annotations, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, front-loaded with the tool's purpose, and no wasted words. It efficiently lists the key metrics and scope.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the low complexity (one optional parameter), full schema coverage, output schema, and annotations, the description is complete. The return format is covered by the output schema, so the description need not elaborate further.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a single enum parameter 'range' that has its own description. The tool description's 'for a window' aligns with the schema without adding extra semantic detail, so it stays at the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description has a specific verb ('Get') and resource ('Google Analytics 4 summary'), clearly distinguishing this tool from sibling summary tools like get_marketing_summary. It lists concrete metrics (sessions, users, conversions, revenue, etc.), making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use for GA4 web analytics summaries but does not explicitly state when to prefer this over sibling tools such as get_marketing_summary or get_dashboard_summary. No exclusions or alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds context by listing the contents of the brand pack, which sets expectations for what is returned. However, it does not disclose additional traits like response format or authentication requirements, though the output schema fills some gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the core concept ('Brand identity configuration') and efficiently lists specific elements. There is no wasted language, and it is appropriately sized for the tool's simplicity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless read tool with an output schema and read-only annotations, the description adequately explains what the tool returns. It could mention whether this is scoped to the current account or workspace, but overall it is complete enough for such a straightforward getter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so schema description coverage is trivially 100%. Per rubric, 0 parameters baselines at 4, and the description adds no parameter semantics because none are needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly defines the tool's resource as brand identity configuration and enumerates its components (logo, colors, fonts, voice attributes, banned phrases, required disclaimers). The 'get' verb is in the tool name/title, making the retrieval intent clear, but the description itself lacks an explicit verb and does not distinguish from siblings like get_brand_score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as get_brand_score or get_account_profile. There are no exclusions, prerequisites, or context about when this tool is the appropriate choice, leaving the agent without selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and destructiveHint, and the description adds value by explaining the weighted-average composition, the time scope ('latest day'), and the return contents (score + listing count). This goes beyond the safety profile, though it does not cover authentication or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the main purpose, and every phrase adds meaningful context. There is no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with no parameters and an output schema, the description is complete: it explains what the score is, how it is computed, and what is returned. No additional context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and the schema is empty, so the baseline of 4 applies. The description cannot add meaning beyond the schema, but nothing is missing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns the latest brand-health score for the workspace, defined as a weighted average across tracked marketplace listings with specific components. It distinguishes itself from siblings like get_brand_pack by focusing on a health metric rather than brand assets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The usage is implied: use this to get the brand-health score. However, there is no explicit guidance on when to choose this over other analytics tools or any exclusion criteria, so it falls at the 'implied usage' level.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds behavioral context by specifying that it returns only synced order counts, not raw orders, and clarifies it's an overview/aggregate view.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences and immediately states the output and purpose. It is front-loaded with the key information and avoids any filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple (no parameters, read-only, output schema present) and the description fully covers its behavior and use case. Combined with strong annotations and an output schema, no additional context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is empty (0 parameters), so the baseline is 4. The description doesn't need to elaborate on parameters since there are none; it instead focuses on what the tool returns.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns order counts per channel for non-Amazon marketplaces, listing them explicitly. It distinguishes itself from sibling summary tools by specifying the exact scope (non-Amazon marketplaces) and the output type (synced order count per channel).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear use case: 'use it to see which marketplaces have data and their relative scale.' It gives context but does not explicitly mention alternatives or when not to use this tool, so it misses the top score for explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations already indicating read-only and non-destructive behavior, the description adds value by specifying the exact output content: open and escalated counts, channel breakdown, and recent violations. It does not contradict the annotations, and it provides behavioral context about what data is returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the full term for the acronym and lists the key outputs. Every word contributes to understanding the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters, an output schema exists, and the annotations cover safety, the description is sufficiently complete. It explains the domain (MAP compliance) and the content returned without extraneous details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and the schema is empty. According to the baseline for no parameters, the score is 4. The description does not need to explain parameter semantics since there are none.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: retrieving MAP/MRP compliance violations with specific components (counts, channel breakdown, recent violations). It uses the full term 'Minimum-advertised-price' to disambiguate the acronym, and there is no overlapping sibling tool, so it effectively distinguishes itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for accessing compliance violation data, but it does not explicitly state when to use it over alternatives. However, there are no sibling tools with similar functionality, so the lack of exclusions is acceptable. The context is clear enough for an agent to select it when needing compliance violation metrics.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds that the tool provides integration statuses and recent activity, which is useful but does not disclose deeper behaviors like response size or pagination. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler. The first sentence front-loads the core content; the second gives usage guidance. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the zero-parameter input, explicit annotations, and an output schema, the description fully covers the tool's purpose, use case, and scope. No additional context seems necessary.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and the description correctly does not discuss any. Baseline of 4 applies since there is nothing to clarify.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns 'high-level health of the workspace: connected integrations by status and the most recent account activity.' This specific content scope, combined with 'Use this first', distinguishes it from sibling summary tools like get_analytics_summary and get_orders_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states 'Use this first to answer how is my business set up / what's connected', providing a clear use case. However, it does not mention when to use alternative tools or any exclusions, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context beyond annotations by detailing the output contents (aging buckets, fee exposure, recommended actions), which helps the agent understand what the tool computes without contradicting the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, tightly packed sentence that conveys the tool's scope, key outputs, and examples without any filler. It is front-loaded with the essential purpose ('Amazon FBA inventory health') and immediately provides concrete details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no parameters and an output schema present, the description only needs to convey what the tool covers and returns. It does so comprehensively: aging buckets, fee exposure, and recommended actions. The presence of an output schema means return format details need not be in the description, so this is complete for invocation and selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so schema coverage is trivially 100% and the description cannot add parameter meaning. Per rubric, 0 params earns a baseline of 4. The description focuses on the output semantics rather than parameters, which is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns FBA inventory health with specific details: aging buckets (0-90 to 365+ days), long-term storage-fee exposure, and recommended actions. This specific verb+resource pairing distinguishes it from sibling tools like get_inventory or get_stock_status, which focus on raw inventory levels rather than health and recommendations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention exclusions or reference sibling tools such as get_inventory, get_analytics_summary, or get_dashboard_summary, leaving the agent to infer appropriateness solely from the tool's name and title.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds behavioral context by listing what data is included (section totals and HSN rollup) and the purpose (return preparation). It does not mention data freshness or auth, but the read-only nature is well covered by annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that packs the resource, scope, included data, and use case without wasted words. Every phrase contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a single well-documented parameter, full schema coverage, read-only annotations, and an output schema, the description provides sufficient context. It explains the tax form and its contents, making the tool's role clear. No further details about return values are needed given the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single period parameter, including an enum and default value. The description only reinforces 'for a period' without adding meaning beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides a GSTR-1 outward-supply summary for a period, specifying the included sections (B2B/B2CL/B2CS) and HSN-wise rollup. This distinguishes it from sibling tax tools like get_hsn_summary or get_tax_summary by naming the exact resource and scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'for return preparation' gives clear context for when this tool is appropriate. It does not explicitly exclude alternatives, but the focused scope makes the intended use obvious. A minor gap is the lack of explicit comparison to similar siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds a scope (per-HSN) but no extra behavioral traits like rate limits, data coverage, or side effects. It does not contradict annotations, but also does not go beyond them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that immediately states the tool's purpose and contents. Every word earns its place, with no redundant fluff or repetition of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple tool with one optional parameter, full schema coverage, clear annotations (read-only), and an existing output schema, the description provides enough context for an agent to select and invoke it correctly. No critical information is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with the 'period' parameter fully documented by an enum and default values. The description's phrase 'for a period' only repeats the schema concept without adding format, examples, or additional meaning. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb-phrase 'Per-HSN-code tax rollup' and lists concrete contents (taxable value, CGST/SGST/IGST/cess, invoice count). This clearly distinguishes it from sibling tools like get_gstr1_summary or get_state_wise_tax by focusing on HSN-level aggregation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for tax summaries by HSN code and a period, but it does not explicitly state when to choose this tool over alternatives such as get_tax_summary or get_gstr1_summary. No exclusions or alternative recommendations are provided, so guidance is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations already declaring readOnlyHint=true and destructiveHint=false, the description adds useful behavioral context beyond them: the exact stock fields returned, the join to master product, optional search behavior, and the 25-row cap. It does not contradict annotations and provides transparency into the result shape and limit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that covers purpose, fields, search, and row limit with zero fluff. Every clause adds value and the structure makes it easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists and there are only two optional parameters, the description is complete enough. It explains what data is returned, the join context, and the limit. Minor gaps like sorting or default behavior without query are not critical since the schema and output schema cover the rest.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already describes both parameters (limit and query) with 100% coverage. The description restates 'Optional free-text search by SKU' and 'returns up to 25 rows', which mirrors the schema without adding new syntax or format details. This is the baseline 3 where the schema carries the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns warehouse stock levels by SKU (available, reserved, incoming, blocked) joined with master product data, with optional search. The verb 'Get' plus specific fields and the mention of 'joined to the master product' distinguish it from sibling tools like search_inventory and get_stock_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied: use this to get stock levels by SKU with a row limit. However, there is no explicit when-to-use vs alternatives, no exclusions, and no mention of when to prefer search_inventory or other sibling tools. This places it at 'implied usage' rather than explicit guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the operation as read-only and non-destructive. The description adds valuable context beyond annotations: the PDF link is short-lived, and the manifest contains specific data elements (shipment, order IDs, state). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no redundant information. It immediately states the scope ('One manifest') and lists the key output components and the short-lived link, making it highly concise and structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with one parameter and an output schema, the description adequately covers the returned data (shipment, order IDs, state, PDF link). No additional information is necessary; the output schema handles structural details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description for the single 'id' parameter is complete (100% coverage), stating it is the manifest id. The tool description adds no additional parameter semantics beyond confirming it returns one manifest. Baseline 3 applies when schema covers parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves a single manifest with shipment and order ID lists, state, and a short-lived PDF link. This distinguishes it from list_manifests and other get_* tools, and the title 'Get manifest detail' reinforces the specific purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool should be used when needing details for a specific manifest (since it takes an id and returns one manifest), but it does not explicitly contrast with list_manifests or other alternatives. No exclusion criteria or explicit when-to-use guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description supplements the annotations by disclosing the row limit ('Returns up to 25 rows') and the configuration scope (COGS and platform-fee percentage per channel). It does not contradict the readOnlyHint and adds value beyond the structured safety flags.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, information-dense sentence that conveys purpose, content, and behavior without redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with one optional parameter and an output schema, the description provides adequate context by explaining the data type and row cap. It does not delve into pagination or ordering, but these are not necessary given the schema and annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides 100% coverage of the single 'limit' parameter, including its default and maximum. The description adds no additional parameter-specific guidance; the mention of 'per channel' refers to the data structure, not a query parameter, so it does not enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource (per-product margin configuration) and specifies its contents (COGS and platform-fee percentage, optionally per channel). It distinguishes this tool from sibling get_* tools by focusing on margin/cost models, not just generic analytics or P&L summaries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'used for P&L' provides a clear context for when to use this tool, but it does not explicitly name alternative tools or exclusions. With many get_* siblings, more explicit differentiation would be helpful, but the context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate read-only and non-destructive behavior. The description adds valuable behavioral context by enumerating the exact metrics returned (spend, impressions, clicks, conversions, revenue, ROAS, CTR, CPC), including prior-period deltas and per-platform breakdown. This goes beyond the annotations but does not cover all possible behavioral aspects (e.g., auth, rate limits).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, densely informative sentence. It is front-loaded with the core concept ('Cross-platform ad performance'), lists all key metrics, and includes the per-platform breakdown detail without any wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one optional parameter), full schema coverage, read-only annotations, and an output schema (signaled in context), the description is complete. It specifies the data returned, the breakdown, and the window concept, leaving no critical gaps for an AI agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers the single parameter 'range' 100%, including its enum values and default. The description's mention of 'window' aligns with this parameter but does not add new semantics beyond the schema's already complete documentation. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: retrieving cross-platform ad performance metrics (spend, impressions, clicks, etc.) for a specified time window. It is specific and distinguishes this summary tool from analytical siblings like get_analytics_summary or get_dashboard_summary by explicitly naming marketing/ad metrics and platforms.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (to get ad performance across platforms) but does not explicitly state alternatives or exclusion criteria. There is no guidance on when not to use it or how it differs from similar summary tools, so the usage context is clear but not fully articulated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the operation as read-only and non-destructive. The description adds value beyond the annotations by specifying the response shape—counts by type and severity plus recent events—which sets expectations for the output granularity and content.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, information-dense sentence with no filler. It front-loads the core subject and efficiently includes scope, examples, and output characteristics, making every word earn its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with one optional parameter and a provided output schema, the description covers the domain, temporal context, and result format adequately. No critical usage information is missing, and the tool's behavior is predictable from the annotations and description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema fully documents the single 'days' parameter with range and default, and schema coverage is 100%. The description's 'window' wording aligns with the parameter but doesn't add new semantic details, so the baseline of 3 for high schema coverage applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies the tool retrieves marketplace alert events, listing concrete examples (price drops, OOS, MAP breaches) and the output structure (counts by type/severity, most recent events). This distinguishes it from sibling tools like get_notifications or list_qradar_alerts, which target different domains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'fired in a window' conveys a temporal filtering use case, and the description implies the tool is for summarizing alert activity over a lookback period. It gives clear context for when to use it but does not explicitly name alternatives or exclusions, so it falls just short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the read-only and non-destructive nature, and the description adds that alerts include severity, title, and state. However, it does not disclose details like ordering, limits, or whether it returns only unread notifications, leaving some behavioral aspects unspecified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that front-loads the resource ('in-app notifications inbox') and immediately lists key attributes. There is no fluff or redundancy, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters, read-only annotations, and an output schema, the description provides sufficient scope ('recent alerts') and content fields. The output schema covers return details, so nothing essential is missing for such a simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. There is no parameter schema to describe, and the tool's behavior is self-contained, so the description does not need to compensate for any missing parameter information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as an in-app notifications inbox showing recent alerts with severity, title, and state. It is specific to the notifications resource and distinct from sibling tools, though it lacks an explicit verb like 'retrieve' or 'list', making it slightly less direct than ideal.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended use case is implied: if you need recent in-app notifications, this is the tool. However, there is no explicit guidance on when to choose this over alternatives or any mention of exclusions, which is a minor gap for such a simple read-only tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description adds valuable context by detailing what the response includes (line items, lifecycle transitions, credit consumption). This goes beyond the structured fields and helps the agent understand the scope of the read operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose ('Full detail for one fulfillment order'), then efficiently lists the key data categories. No filler or redundant information appears.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a single parameter, output schema present, and annotations covering safety, the description provides sufficient context. It names the source for the id and the specific detail areas, making the tool's behavior clear without needing extra explanation of return format (handled by output schema).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with id described as 'The OMS order id.' The description adds the crucial guidance to obtain this id from search_oms_orders, providing practical source information that the schema alone does not convey. This elevates the baseline from 3 to 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides 'Full detail for one fulfillment order' and enumerates specific fields (line items, lifecycle history, credit consumption, etc.). This distinguishes it from sibling tools like get_order or search_oms_orders by focusing on a single OMS fulfillment order with complete details.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly instructs the user to 'Get the id from search_oms_orders', providing a concrete workflow for retrieving the required parameter. It implies use for single-order detail but does not explicitly state when to prefer this over alternatives like get_order.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate a safe read operation. The description adds that money is in minor units (paise for INR) and that a linked return is included if present, which are non-obvious behavioral details not covered by annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core purpose, no filler. The second sentence conveys currency units and ID sourcing efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a robust output schema and annotations, the description sufficiently explains scope (single order), included data, and currency units. It could be slightly more explicit about differentiation from get_oms_order but is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover both parameters at 100%. The description adds that these identifiers come from search_orders, providing sourcing context beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves full detail for a single order by channel and line-item ID, distinguishing it from summary/list tools like get_orders_summary and search_orders. It also specifies included data (linked return, channel-specific fields), making the purpose specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description instructs to obtain channel and lineItemId from search_orders, establishing a clear workflow. It implies use when full single-order detail is needed, but does not explicitly contrast with alternatives like get_oms_order.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds minimal behavioral context beyond what the annotations provide, such as the temporal window and aggregation, but no extra traits like data freshness or pagination.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core function and followed by the intended use. Every word earns its place with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a simple one-parameter schema with full coverage, an output schema, and read-only annotations, the description adequately conveys what the tool does and when to use it. No further context is necessary.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single 'days' parameter, which is already described as the lookback window. The description mentions 'window' but does not add syntax or default-value details beyond the schema, so it does not elevate beyond the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb+resource: 'Order volume per channel over a window, across all connected marketplaces.' It clearly distinguishes from sibling tools like get_channel_orders_overview by emphasizing all marketplaces and relative scale per channel.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context: 'Use it to see where orders are coming from and the relative scale per channel.' It does not explicitly mention when not to use this tool or name alternatives, but the intended use case is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is known. The description adds output details (net amount, count per channel) but no additional behavioral context such as data freshness, aggregation specifics, or limitations. It does not contradict annotations, so a neutral score is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one sentence, front-loaded with the key concept 'Settlement/payment activity', and precisely states the main outputs. No unnecessary words or repetition; it is highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one optional parameter, output schema present, annotations provided), the description is adequate. It explains the high-level purpose and key outputs without needing to detail return fields (output schema covers that). A small gap is the undefined term 'major units' and lack of clarity on 'per channel', but these are minor for a summary tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description for the single 'days' parameter is complete (100% coverage), stating it is a lookback window with a default of 30. The description does not add any further meaning or examples, so it relies on the schema for parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: it returns the net amount Amazon settled and the count of settlement/payment records synced per channel. The verb 'get' and resource 'payments summary' are specific, but the description does not explicitly differentiate it from sibling summary tools like get_orders_summary or get_reimbursements_summary, though the unique focus on settlements/payments is implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use this tool (when needing settlement/payment activity summaries) but provides no explicit guidance on when to prefer it over alternatives or when not to use it. It does not mention sibling tools or any exclusions, so the usage context is inferred rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds useful behavioral context by noting the pick-PDF link is 'short-lived', which is not inferable from annotations or the schema. It also lists the returned fields, giving the agent a clear picture of the output without needing to inspect the output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that front-loads the key idea ('One picklist') and efficiently lists the main fields. Every word adds value, with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple get-by-id tool with 1 parameter, full schema coverage, and an output schema, the description provides sufficient context: it identifies the resource, the key fields, and the short-lived link. The annotations confirm safety, and the output schema covers return values, so no additional explanation is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% – the 'id' parameter is described as 'The picklist id.' The description does not add any additional meaning beyond this, so it relies on the schema for parameter semantics. Baseline 3 is appropriate given the schema fully documents the parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'One picklist' which clearly indicates this tool retrieves a single picklist's detail, and the title 'Get picklist detail' provides a specific verb and resource. It distinguishes from sibling tools like list_picklists by focusing on a single instance with specific fields.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used when you need details for a specific picklist (e.g., after obtaining an ID via list_picklists), but it does not explicitly state when to use it over alternatives or mention any prerequisites. There is no direct comparison to list_picklists or other sibling tools, so guidance is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds valuable behavioral context by specifying the data source (Amazon settlements), the included line items, and that amounts are in major currency units. This enriches understanding beyond annotations without any contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-organized sentence that front-loads the core purpose ('Amazon settlement-based money summary') and then efficiently lists the included components. Every phrase adds value, and there is no redundant or filler text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description does not need to detail return structure. It covers data source, window concept, included components, and units—sufficient for a straightforward summary tool with one optional parameter. No critical context is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single 'days' parameter, which is fully described in the schema as a lookback window with default 30. The description's phrase 'over a window' aligns but adds no new semantic detail beyond the schema. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Amazon settlement-based money summary over a window.' It explicitly enumerates the financial components included (revenue, fees, refunds, TCS/TDS, net amounts, reimbursements), which clearly distinguishes it from sibling summary tools like get_payments_summary or get_reimbursements_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool: when an Amazon settlement-based money summary over a window is needed. It does not explicitly name alternatives or exclusion scenarios, but the context is unambiguous enough to guide selection among the many summary-focused siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds meaningful context: the requirement of a Q-Radar subscription and the exact meaning of 'movers' (products losing estimated sales to out-of-stock), which goes beyond the structured annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence front-loaded with the key concept, followed by a clarifying clause and a subscription note. No words are wasted; it is both concise and complete.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with only two optional parameters and an output schema, the description covers the essential aspects: what it does, the domain, the metric, the window, and an access requirement. It is sufficiently complete for an agent to decide when and how to invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions for both parameters ('Lookback window in days (default 7)' and 'Max movers (default 10)'). The description adds no further parameter detail, but the schema already does the heavy lifting, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as 'Top potential-sales-loss (PSL) movers from quick-commerce shelf intelligence over a window', explaining exactly what it returns (products losing the most estimated sales to out-of-stock, by channel). This specific verb+resource+scope distinguishes it from sibling Q-Radar tools like get_qradar_overview or get_shelf_availability.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context: use this to see PSL movers over a lookback window, and it notes the prerequisite of a Q-Radar subscription. It does not explicitly state when not to use it or list alternative tools, but the use case is evident from the metric definition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety profile is covered. The description adds useful context about the output content (distribution, gaps, opportunity value) and the expansion scoping, which goes beyond the annotations and helps the agent understand what kind of analysis this tool supports.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loads the core output, and includes a practical use case. Every phrase carries meaning with no fluff or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and good parameter descriptions, the description is reasonably complete. It explains what kind of result to expect (percentages, rankings, pincode gaps) and provides a clear use case. It lacks explicit details on default behavior or parameter combinations, but these are not critical given the schema and output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75% (three params described in the schema), but the description adds meaning for the storeType param by naming 'express / instant / longtail' in the output context. It also frames the coverage filter and platform in terms of expansion analysis, providing extra semantic value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: it provides numeric distribution percentages, store-type reach, per-state coverage, and a ranked gap pincode list. It distinguishes itself from other Q-Radar tools by emphasizing expansion gaps and opportunity value, and it names a specific use case ('where should I expand on Blinkit').

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly gives a usage context ('Use for where should I expand on Blinkit'), which tells the agent when this tool is appropriate. It does not explicitly mention when not to use it or name alternative tools, but the use case is clear enough to differentiate it from siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's job is lighter. It adds significant context: the ledger is 'ranked by impact', contains data in paise with an explicit instruction to 'convert to ₹', and includes unique fields like an 'audit hash chain'. This helps the agent understand the tool's output semantics beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, information-dense sentence that front-loads the core purpose ('CFO-grade potential-sales-loss ledger') followed by specific details. No filler or redundant phrases. It efficiently conveys the key data points, units conversion, and ranking in a compact form.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only list tool with an output schema and rich annotations, the description covers the essential behavioral aspects: what data is included, the conversion instruction, and the ranking. It lacks explicit guidance on when to use it (covered in dimension 2) but is otherwise complete given the schema and annotations. The existence of many qradar siblings with no differentiation means a bit more context would have made it a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters like limit, sortBy, dateRange, and platforms are fully documented. The description adds almost nothing about parameters; 'Ranked by impact' hints at a sort order consistent with the default sortBy, but that information is already in the schema. The baseline of 3 is appropriate since the schema carries the parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies this as a 'potential-sales-loss (PSL) ledger' with specific contents: 'each out-of-stock window with lost units and lost revenue', 'velocity basis, price/MRP, and an audit hash chain'. This goes beyond just naming the tool and distinguishes it from siblings like get_psl_movers or get_qradar_overview through the audit hash chain and CFO-grade qualifier.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. The 'CFO-grade' phrasing implies a financial analysis context, but the description does not mention any exclusions, prerequisites, or sibling tool comparisons. It is unclear whether this should be preferred over get_psl_movers or get_qradar_overview in specific scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: PSL is returned in paise (with a note to convert to ₹) and the output includes a daily trendline. This helps the agent understand unit handling and output structure without contradicting the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first lists the contents in a compact, front-loaded manner; second gives a single concrete use case. No wasted words, no repetition of schema details, and all information earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (multiple KPIs) and that an output schema exists, the description provides sufficient context: it names all major output components, flags the PSL unit conversion pitfall, and positions the tool as a headline/overview. This is complete for an overview tool, especially with a rich output schema to back it up.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%—every parameter has a clear description in the schema, so the baseline is 3. The tool description does not add additional parameter semantics beyond listing high-level output fields (e.g., pincode coverage) that loosely relate to filters, but no new syntax or behavior is introduced. The schema already does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the specific verb+resource: 'quick-commerce shelf-intelligence headline' and enumerates exact KPIs returned (OSA %, shelves & SKUs tracked, risk score, PSL, pincode coverage, trendline). This distinguishes it clearly from sibling overview tools like get_analytics_summary or get_dashboard_summary by naming its unique focus on availability and PSL.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides an explicit use case: "Use for 'how is my quick-commerce availability'." This is clear contextual guidance. However, it does not mention when not to use it or name alternatives (e.g., get_shelf_availability for detailed shelf data), so it stops short of full exclusion/alternative guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds behavioral context by detailing the data granularity (pincodes, dark-stores) and included metrics (risk score, lever scores, inventory, price), going beyond the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly packed sentences, no filler. The first defines scope and outputs; the second gives lineage. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and all parameters documented, the description sufficiently covers purpose, scope, and prerequisite. No critical information is missing for selecting and invoking the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds meaning by clarifying that masterId refers to a single product and by directing users to list_qradar_skus for the value, which is helpful beyond the schema's simple field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies a 'time-series of shelf evaluations for one master product across pincodes and dark-stores', listing concrete metrics. This clearly distinguishes it from sibling tools like get_qradar_overview or list_qradar_skus, and even explains how to obtain the required master id.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context for when to use the tool (time-series history for one product) and explicitly points to list_qradar_skus for obtaining the master id. It does not mention exclusions or alternatives, but the usage context is evident.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds useful behavioral context: it reports organic/sponsored presence, covers top 5/10/20 positions, and supports keyword filtering or listing top organic keywords. No additional risk disclosure is needed given the safe read-only annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences that front-load the core metric and immediately state use patterns. Every clause adds value without repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only analytical tool with an output schema, the description conveys the metric, scope, position tiers, and filtering/sorting behavior. It is complete enough for an agent to select and invoke the tool correctly without missing critical context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already covers 80% of parameters with meaningful descriptions (limit, keyword, dateRange, platforms) and self-explanatory enum values for sortBy. The description only reinforces keyword filtering and highest-organic sorting, adding no new parameter-level semantics, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as reporting keyword share-of-search on quick-commerce, specifying organic and sponsored presence in top 5/10/20 results per keyword and channel. This distinguishes it from sibling qradar tools like get_qradar_overview or get_qradar_distribution.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides concrete usage guidance: filter to one keyword or list the highest-organic keywords. It clearly communicates the tool's context but does not explicitly name alternatives or when-not-to-use conditions, so it falls just short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds context about the window and output metrics, but does not disclose any additional behavioral traits like data latency, currency units, or aggregation specifics. It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the key information (Amazon FBA reimbursements) and lists the output components without unnecessary words. It is highly concise and scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one optional parameter, an output schema exists, and annotations cover safety. The description adequately covers the purpose, scope, and key outputs, making it complete for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the sole parameter 'days' is well-documented in the schema. The tool description adds little beyond the word 'window' which aligns with the schema, so it does not provide significant additional meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: retrieving an Amazon FBA reimbursements summary. It specifies the key metrics (total amount, count, units, top reasons) and the resource (reimbursements), distinguishing it from sibling tools like get_payments_summary or get_returns_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context (need a reimbursement summary over a window) but does not explicitly mention when to prefer this tool over alternatives or when not to use it. There are many similar summary tools among siblings, so more explicit guidance would be helpful.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds the window-based behavior and the output content (count, units, reasons, dispositions). However, it does not disclose any additional behavioral traits like data freshness, pagination, or edge cases. Given annotations, a 3 is appropriate as it adds some value but lacks rich behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is front-loaded with the tool's purpose and output details. Every word earns its place, with no fluff or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one optional parameter and an output schema, the description sufficiently explains what the tool does and its primary outputs. It is not overly complex, and the output schema handles return value details. A slight gap is that it doesn't mention the default window, but that is covered by the schema. Overall, it is quite complete for its complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has one parameter 'days' with a complete description (lookback window, default 30). Schema coverage is 100%, so the baseline is 3. The description only vaguely references 'over a window' without adding new meaning beyond the schema, so it does not elevate the score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: it provides Amazon returns summary over a window, specifically listing total count, total units, and top return reasons and dispositions. This is a specific verb (get) + resource (returns summary) and distinguishes it from sibling tools like search_returns (detailed returns) or get_orders_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for summary-level views of returns over a configurable window. It clearly communicates the context (summary over a window) but does not explicitly exclude alternatives or mention when to use other tools. This qualifies as 'clear context, no exclusions'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds the prerequisite of the SEO module and indicates an aggregated summary. It does not contradict annotations, but provides no further behavioral detail beyond that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one concise sentence that front-loads the purpose and includes the key prerequisite. Every word contributes value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple tool (one fully documented parameter, output schema, and read-only annotations), the description provides all necessary context for selection and invocation. It also highlights the SEO module requirement, making it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully documents the 'range' parameter with enum values and a default (28d). The description only references a 'window' without adding new meaning, so it meets the baseline for high schema coverage but doesn't exceed it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides a Google Search Console summary with top queries and specific metrics (impressions, clicks, average position, CTR). It specifies the resource (GSC search queries) and distinguishes it from sibling tools by naming the data source.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context: it is a GSC summary for a time window and requires the SEO module. It does not explicitly state when not to use it or name alternatives, but the GSC-specific scope is sufficient to infer appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=true and destructiveHint=false. The description adds useful behavioral context beyond annotations by specifying that only tracked keywords are returned and that the SERP module is required—an authorization/module prerequisite. It does not cover error conditions or response behavior, but the annotations lower the bar.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences and about 15 words total. It front-loads the key return fields and adds the module prerequisite without any filler. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with one optional parameter and a full output schema, the description provides sufficient context: it states what is returned and the module requirement. The annotations confirm safety, and the output schema covers return structure, so there are no critical gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully describes the single optional 'search' parameter as a free-text keyword filter, with 100% schema description coverage. The description adds no additional parameter semantics, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource (tracked SEO keywords) and the specific data returned (current rankings, search volume, intent, rank trend). The verb is implied by the tool name 'Get'. However, it does not explicitly distinguish itself from the sibling tool get_seo_queries, though the specific fields provide some differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states the prerequisite 'Requires the SERP module' and implies usage for viewing keyword rankings, but it provides no explicit guidance on when to choose this tool over alternatives like get_seo_queries or search. No exclusions or alternative recommendations are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable context beyond annotations: the 7-day time window, per-channel aggregation, value interpretation ('lower is worse'), and the subscription requirement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences efficiently convey the metric, time range, channel breakdown, interpretation, and access requirement, with no redundant or excessive wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that there are no parameters, the output schema exists, and read-only annotations are present, the description covers all essential behavioral context including the metric, time window, channel dimension, interpretation, and subscription prerequisite.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

This tool has zero parameters, so schema coverage is trivially 100%. The baseline for zero-parameter tools is 4, and no additional parameter detail is necessary or provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies the metric (OSA%), time range (last 7 days), and dimension (per channel), and explains the metric's meaning with an interpretation ('lower is worse'). It distinguishes itself from sibling Q-Radar tools by focusing specifically on shelf availability.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for monitoring quick-commerce shelf availability and notes the Q-Radar subscription prerequisite, but it does not explicitly state when to use this tool versus related Q-Radar tools like get_qradar_overview or list_qradar_skus.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, confirming a safe read operation. The description adds context about the returned dimensions (state-wise, tax types, invoice counts) but does not disclose additional behavioral traits like permissions, data freshness, or response size. With annotations covering safety, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, information-dense sentence that front-loads the key output (per-state outward-supply and tax breakdown) and packs supporting details into a parenthetical. Every word contributes, and there is no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given one optional parameter, clear read-only annotations, and the presence of an output schema, the description is largely complete for selection and invocation. It could mention the source document (e.g., GSTR-1) for extra clarity, but this is not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage for the sole parameter (period) is 100%, with an enum and description already provided. The tool description only mentions 'for a period' without adding syntax or format details, so it adds no meaningful value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's output: a per-state outward-supply and tax breakdown with specific components (taxable value, CGST/SGST/IGST, invoice count, intra/inter-state) for a period. This level of specificity distinguishes it from sibling tax-related tools like get_tax_summary or get_hsn_summary, which focus on other aggregations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance is provided on when to use this tool versus alternatives such as get_tax_summary or get_gstr1_summary. The description only explains what the tool returns, leaving the agent to infer usage context from the tool name and sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safe read nature is known. The description adds that it returns a sample of currently out-of-stock listings, implying not all are returned, and mentions a breakdown by channel, which is useful behavioral detail beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that efficiently enumerates the output components without waste. Every phrase contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters, read-only annotations, and an existing output schema, the description sufficiently conveys the tool's scope and return contents. It could clarify what 'tracked marketplace listings' means, but this is a minor gap for a low-complexity tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema fully covers parameter semantics (vacuously). Per instructions, baseline is 4 when there are no params, and the description does not need to add parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool reports out-of-stock status across tracked marketplace listings, listing specific output elements (total listings, OOS count, breakdown, sample). It distinguishes from generic inventory tools by focusing on OOS, though it does not explicitly name sibling alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like get_inventory or get_shelf_availability is provided. The description only states what it returns, leaving usage context implied at best.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description only needs to add context. It does so by specifying the return contents (per-line drift amounts, workflow state) and the default state filter, which goes beyond the structured data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, well-structured sentence that front-loads the core purpose and packs in the essential details without fluff. It is immediately scannable and highly informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool with one parameter and an output schema, the description is complete. It explains the concept, what is returned, and the default behavior, allowing an agent to select and invoke it correctly without additional context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a detailed enum description for 'state', so the description adds little beyond what the schema already provides. The 'Defaults to open items' note is already in the schema's default value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: it returns lines where tax doesn't equal rate × taxable value, with per-line drift amounts and workflow state. This verb+resource definition distinguishes it from sibling tools like get_tax_summary or get_state_wise_tax.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'drift audit' gives a clear use case, and 'Defaults to open items' indicates the typical scenario. However, it does not explicitly name alternative tools or state when not to use it, so it falls short of a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safe/read-only nature is covered. The description adds that the tool returns an aggregated snapshot with invoice count splits and TCS/TDS per channel, which provides some behavioral context beyond the schema, but it does not disclose details like default period handling or data-source caveats.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One compact sentence delivers the tool's purpose, scope, and key output fields, ending with 'India GST' for regional context. No filler or repetition of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a simple optional parameter, full schema coverage, a read-only annotation, and an existing output schema, the description provides enough context for an agent to understand what the tool does and when to invoke it. The inclusion of B2B/B2C split and channel-level TCS/TDS adds useful completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single 'period' parameter is fully documented in the schema with an enum and default value, and the description's phrase 'for a period' aligns with it but adds no new semantic detail beyond the schema. Baseline 3 is appropriate given the 100% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies a GST tax summary for a period, enumerating the exact components returned (taxable value, CGST/SGST/IGST/cess, TCS, TDS). It is distinct from sibling tools like get_state_wise_tax or get_gstr1_summary by focusing on a period-based aggregate snapshot, though it does not explicitly name those alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: use this for a period-level GST snapshot in India, with a defined list of included figures. It does not explicitly state when not to use it or name alternative tools, but the scope is specific enough to indicate its intended use case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations already declaring readOnlyHint and destructiveHint false, the description adds valuable behavioral context: balances are in minor units requiring conversion to ₹, includes free and paid components, exposes expiry and recharge tiers, and is separate from AI wallet. No contradictions with annotations; it complements them well.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loads the core purpose, and includes only essential details: what is returned, unit conversion, and separation from AI wallet. No redundancy or fluff; every phrase serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, read-only tool with an output schema, the description is complete. It covers the key return elements (balance, expiry, recharge tiers), unit conversion guidance, and the distinguishing context from the AI wallet. The output schema likely contains detailed fields, so the description need not enumerate them.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so per the baseline, a score of 4 is appropriate. The description adds no parameter-specific info (none needed), but it explains the output semantics which indirectly clarifies the absence of parameters. The input schema is empty, and the description provides meaning about what the tool returns.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves the fulfillment-credit wallet balance, including free and paid credits, expiry, and recharge tiers. It explicitly distinguishes itself from the AI wallet, helping the agent identify the correct resource. The verb 'get' is implied, and the resource is specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context that this is for fulfillment credits and notes separation from the AI wallet, which guides the agent away from alternative tools like get_ai_wallet. However, it does not explicitly name or list alternative tools or exclude other financial tools, so it falls short of a perfect score.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is clear. The description adds the prerequisite that the campaigns module must be enabled, which is useful context. It does not disclose other behaviors like pagination or error handling, but annotations cover the main safety profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that packs in the resource, platform scope, performance metrics, and module requirement. No wasted words, front-loaded with the essential action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with two optional parameters, no required parameters, an existing output schema, and strong annotations, the description provides sufficient context. It states what is returned, the platform coverage, and the module prerequisite, making it complete for an agent to select and invoke.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both 'range' and 'platform' documented in the schema. The description mentions 'for a window' which vaguely maps to the range parameter, but adds no specificity beyond the schema. This is the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists ad campaigns across connected platforms and includes per-campaign performance metrics (spend, conversions, ROAS, status). This is a specific verb+resource+scope, distinguishing it from aggregated summary tools like get_marketing_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context that it requires the campaigns module and covers connected platforms, implying when to use it. However, it does not mention alternatives or explicitly state when not to use this tool compared to other listing/summary tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds meaningful behavioral context: it mentions the content (issues/opportunities, severity, state, action plans) and notes that state defaults to open. This goes beyond the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single 18-word sentence that front-loads the main purpose and efficiently packs in key attributes (severity, state, action plans, default filter). No unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple schema (1 optional param, no required fields) and the presence of an output schema, the description covers purpose, content, and default behavior sufficiently. It doesn't need to explain return values because output schema exists, though it could hint at pagination or result limits.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with the 'state' parameter having an enum and its own description. The tool description repeats 'open by default' but does not add new semantics beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists AI Coach recommendations, describing them as an 'inbox' of 'detected issues/opportunities' with 'severity and state' and 'AI-generated action plans'. This specific verb+resource+content clearly distinguishes it from sibling tools like get_notifications or list_qradar_alerts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'inbox' and the default state 'open' imply this is the primary view for coach recommendations, giving clear context. However, it does not explicitly mention alternative tools or when-not-to-use cases, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, providing a clear safety profile. The description adds that competitors are operator-curated and that priority/status are included, which is useful context. It does not mention pagination or return format, but given the tool's simplicity and annotation coverage, a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence that directly states the resource and included fields. There is no fluff or redundancy; every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a simple list tool with no parameters and an output schema. The description covers the essential purpose and the key data fields (priority and status). Since an output schema exists, return-value details are not needed, making the description complete for its complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so the baseline score is 4. The description does not need to explain parameter semantics because there are none.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource (operator-curated competitors) and the key attributes included (priority and status). The verb 'list' is present in the name/title, and the description adds specificity beyond the title. It distinguishes itself from siblings by being the only competitor-related tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or alternative guidance, but the description implies it is for viewing tracked competitors. Since there are no sibling tools directly related to competitors, the lack of exclusions is minimally impactful. Usage is implied rather than explicitly stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds useful context by specifying what the tool returns (connection status, health score, last sync time) and scoping it to the workspace's connected sources, which goes beyond the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that immediately identifies the action and resource, then provides examples and return fields. Every word adds value—no fluff or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and no parameters, the description is nearly complete. It could clarify whether it lists only connected integrations or also disconnected ones, and doesn't mention authentication prerequisites, but these are minor gaps for a simple read-only list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema is fully covered. The description doesn't need to explain parameters, but it clarifies the scope of the listing (workspace's connected channels), which indirectly indicates no filtering. The baseline for 0 params is 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists the workspace's connected channels and data sources, with specific examples and the fields returned (connection status, health score, last sync time). This distinguishes it from sibling tools like list_stores or list_sellers by focusing on integrations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The context implies this tool is for viewing integration statuses, but there are no explicit guidelines on when to use it vs. alternatives. It doesn't mention exclusions or other tools to use instead, so the guidance is implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: the status lifecycle, the included counts and timestamps, and the filtering options. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two succinct sentences: the first states the core purpose and returned data, the second covers filtering. Every word adds value, no redundancy, and the key information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 5 optional parameters, an output schema, and read-only annotations. The description adequately explains the manifest lifecycle, included data, and filter options. Minor ambiguity about whether all statuses are included or just a subset, but the arrow notation implies all three stages.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 80%, so the schema already documents most parameters. The description restates the filter capabilities (warehouse, date range) but does not add meaning beyond what the schema provides. Offset lacks a description in schema, and the description does not clarify it either, so this is baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as listing courier hand-over manifests, specifying the lifecycle stages (draft → submitted → acknowledged) and what data is included (shipment + order counts, timestamps). This distinguishes it from sibling tools like get_manifest (singular) and other list tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states the available filters (warehouse and date range), giving clear context for when to use this tool. It does not explicitly mention alternatives or when not to use it, but the existence of get_manifest for single-record details is implied by the sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows it's safe. The description adds no additional behavioral context like pagination, filtering semantics of includeInactive, or return size. It doesn't contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single concise fragment with no wasted words. Front-loaded with the core resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple list operation, full schema coverage, read-only annotations, and an output schema, the description plus structured fields fully specify the tool. No important gaps for the agent to select and invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with descriptions. The description mentions 'assigned warehouse' and 'active status' which are output fields, not input parameters. No extra meaning added beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource as 'warehouse-floor picker roster' with fields, but doesn't use an explicit verb like 'list' or 'returns'. Combined with the title, it's clear it lists pickers, and it distinguishes from siblings like list_picklists and list_team_members.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives such as list_picklists or list_team_members. No mention of use cases, prerequisites, or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only and non-destructive. The description adds value by revealing the range of states covered and the returned fields (line count, ship date, PDF flag), but it doesn't disclose any edge cases, pagination behavior, or other side effects. Given the strong annotations, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence that leads with the resource and packs in essential state and output details. Every word contributes, and there is no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple, with an output schema available and only two optional parameters. The description sufficiently covers the purpose, state filter values, and key output fields. It could have explicitly stated that it returns a list, but the tool name and pluralization make that apparent. Overall, it's complete for effective selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, but the description enriches the 'state' parameter by enumerating the allowed states (draft → assigned → picking → completed), which the schema does not provide. This helps the agent choose valid filter values. The 'limit' parameter remains fully defined by the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The tool name 'list_picklists' and title make the purpose clear. The description adds context by specifying the state progression (draft → assigned → picking → completed) and key output fields (line count, expected ship date, PDF existence). While it doesn't explicitly say 'returns a list of picklists', the name and context suffice, and it distinguishes from the singular sibling get_picklist.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for viewing pick waves and shows that the 'state' parameter filters by the listed states, but it provides no explicit when-to-use or exclusions. It does not mention alternatives like get_picklist for single-item details. Guidance is implicit rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is established. The description adds context about the content of the alerts (types, severity, affected entities) but doesn't disclose any additional behavioral traits such as default values, pagination, or filtering behavior beyond what the schema mentions. It's acceptable but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence that front-loads the core idea ('Quick-commerce anomaly alerts') and immediately lists the alert types and key attributes. Every phrase adds information and there is no filler. Ideal size for a simple listing tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description doesn't need to explain return values. However, given the large set of QRadar sibling tools, the description lacks guidance on how this tool fits into the broader workflow. It also doesn't mention defaults (e.g., limit default, dateRange default) that are in the schema, but those are already in structured fields. Overall it's adequate but not complete in helping the agent decide when to invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60% (limit and dateRange have descriptions; type, severity, and platforms only have enums). The description mentions 'severity' and 'channel' which weakly maps to the severity and platforms parameters, but it doesn't explicitly walk through each parameter. It adds some meaning over the raw schema but doesn't fully compensate for the undocumented parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as listing quick-commerce anomaly alerts and enumerates the alert categories (out-of-stock spikes, price anomalies, risk escalations, critical-stock events). It also mentions key attributes (severity, affected SKU/channel/pincode), which gives a solid sense of purpose. However, it doesn't explicitly differentiate from sibling QRadar tools like get_qradar_overview or list_qradar_skus, so it's not a perfect 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives. The description says nothing about 'use for X instead of Y' or any exclusions. While the name 'list_qradar_alerts' suggests monitoring alerts, there are many sibling QRadar tools and the description provides no decision-making context for choosing this one.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the tool read-only and non-destructive. The description adds behavioral context about sorting behavior and return fields. The title's 'worst-OSA first' conflicts with the schema default (recent), but the description correctly presents osa_asc as an option rather than the default, avoiding a direct annotation contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact, with three sentences that front-load the core purpose. The final fragment 'Own vs competitor SKUs' is slightly cryptic but not wasteful. Every sentence earns its place, though it could be more structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a rich output schema and fully documented parameters, the description provides enough context for an agent to select and invoke the tool. It explains the primary sorting/filtering use case without redundantly restating schema details, making it complete for a listing tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with parameter descriptions. The description adds semantic value by linking osa_asc to 'worst-availability' and minOsaPercent to filtering under target OSA, which goes beyond the raw parameter names and enums.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists SKUs from the Q-Radar rotation with OSA%, risk score, shelf counts, and pricing. It differentiates from sibling tools by focusing on SKU-level inventory data, but it doesn't explicitly name alternatives like get_qradar_overview or get_qradar_distribution, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives practical usage guidance: use osa_asc to surface worst-availability SKUs, filter by target OSA, and distinguish own vs competitor SKUs. It doesn't state when NOT to use the tool or name a specific alternative, but the context is sufficient for basic selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds context about the data source ('tracked listings') and output fields ('classification and rating'), but does not disclose potential behaviors like pagination, ordering, or rate limits. This is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one concise sentence that communicates the core purpose and scope without redundant words. Every phrase ('observed on tracked listings', 'competitive seller universe', 'classification and rating') adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with two optional parameters and an output schema, the description sufficiently conveys the domain scope. It lacks explicit alternatives or caveats, but the presence of annotations and output schema fills most gaps, making it complete for basic usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for both 'limit' and 'channel', so the schema already provides clear meaning. The description only mentions 'Optional channel filter', which adds no new semantic value beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly identifies the resource (marketplace sellers) and adds specificity with 'tracked listings', 'competitive seller universe', and 'classification and rating'. However, it does not explicitly distinguish from sibling tools like list_competitors, though the focus on sellers provides some implicit differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for viewing competitive sellers via 'observed on tracked listings', but there is no explicit when-to-use or when-not-to-use guidance, nor any mention of alternative tools. The 'Optional channel filter' is parameter usage, not tool selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already provide readOnlyHint=true and destructiveHint=false, so the read-only nature is covered. The description adds valuable behavioral context by stating it lists 'every' connected store, enumerating marketplace types, and specifying the 30-day order count window. This goes beyond the annotations but omits details like possible pagination or ordering behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that packs a lot of useful detail without filler words. It is front-loaded with the action and resource, but the long enumeration of platforms and fields creates a dense sentence that could be structurally streamlined while still being concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and zero parameters, the description covers the essential behavioral scope: what stores are included, what fields are returned, and the timeframe. The tool is straightforward, and the description combined with annotations and output schema provides a complete picture.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema trivially covers everything. According to the rubric, the baseline for 0 params is 4, and the description does not need to compensate for missing parameter information. It effectively explains what the tool returns, which is sufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('List') and resource ('connected store/marketplace account'), enumerates the supported platforms (Amazon, Shopify, Flipkart, etc.), and specifies the exact return fields (display name, country/currency, order count in last 30 days). This clearly distinguishes it from generic siblings like list_integrations and leaves no ambiguity about its function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to prefer this tool over alternatives, nor does it mention any exclusions. Usage is implied from the name and the clear scope, but there is no comparison to similarly named list_* tools or guidance on when a different tool (e.g., list_integrations) would be more appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds the permission prerequisite and clarifies that the output includes roles and effective permissions, providing useful behavioral context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences, with the core purpose front-loaded and no unnecessary words. It earns its place without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple zero-parameter read-only list with an output schema, the description covers the essential purpose and permission requirement. It is complete enough for an agent to understand what the tool does and when it can be invoked.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the schema is trivially complete. The baseline for 0 parameters is 4, and the description adds no parameter details, which is acceptable since none exist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as providing workspace members with their roles and effective permissions. This distinguishes it from sibling list_* tools such as list_sellers or list_integrations, making the purpose specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions a required permission level (org member-read, Owner/Admin), which gives some context for when the tool can be used. However, it does not explicitly state when to use this tool over alternatives, though no direct alternative exists among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool as read-only, non-destructive, and closed-world. The description adds that results are citeable with stable ids and that full detail requires a fetch call, making the output format and follow-up behavior clear. It does not mention pagination or result limits, but the annotations reduce the burden.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loaded with the core purpose, and every clause adds value. It is concise, structured, and free of redundant filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter search tool with an output schema and read-only annotations, the description provides sufficient context. It explains the search scope, the nature of results, and the recommended follow-up action, making it complete for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides full coverage for the single query parameter, describing it as free-text over product title, brand, or SKU. The description repeats this information without adding new semantic details about parameter format, length, or constraints, so it does not elevate the score above the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches the workspace's product catalogue by free text across title, brand, or SKU. It distinguishes this from sibling search tools like search_inventory or search_orders by specifying the product catalogue scope, and from get_* tools by focusing on search and discovery of citeable results.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states it is built for deep-research and retrieval workflows, giving clear usage context. It also instructs to pass an id to fetch for full detail, guiding the user to the appropriate next step. However, it does not mention when not to use it or explicitly name alternatives like search_catalog, so it lacks full exclusion guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds behavioral context by specifying return fields, the max of 25 matches, and advice to narrow queries if results are truncated—going beyond the basic annotation info.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core action and resource, and every detail is useful. There is no fluff or repetition, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple two-parameter tool, full schema documentation, read-only annotations, and an output schema, the description covers all necessary details including truncation behavior. It is complete for an AI agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for both parameters, but the description enriches semantics by explaining that 'query' matches title/brand/SKU and that 'limit' caps results at 25. This adds meaning beyond the schema's field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Search') and resource ('MASTER product catalog'), defines matching fields (title, brand, SKU), and distinguishes it from sibling search tools like search_inventory and search_orders. This satisfies the criteria for specific verb+resource+differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context: free-text search over the master product catalog, with fields like MRP and status. It does not explicitly name alternatives or state when not to use it, but the context is clear enough to guide selection among similar search tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds meaningful behavioral detail: query matches substring against multiple fields, results are master-grain with per-channel/per-store/per-warehouse stock and a health state. This exceeds what annotations provide and helps set expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences: it opens with a clear purpose, then details matching behavior and result structure, then states filters. Every sentence contributes useful information with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and thorough parameter descriptions, the tool description is complete enough. It covers query semantics, result granularity, stock breakdown, health state values, and available filters, so an agent has sufficient context to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description goes beyond the schema by clarifying that the `query` parameter matches product name, accounting SKU, brand, or variant SKU as a substring, and it lists the healthState enum values. This enriches the meaning of the most complex parameter. `limit` and `channel` are already well-described in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Find inventory for a specific product across all channels.' It also distinguishes itself from generic search tools by specifying key matching fields (product name, SKU, brand) and output characteristics (per-channel stock, health state), making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on how to use the tool: search by query and filter by channel or health state. However, it does not explicitly mention when to use this tool over sibling tools like get_inventory or search_catalog, nor does it state exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds value by disclosing the state machine (new → reserved → … → shipped), the fields included (credit status, expected ship date), and the exact filter semantics (e.g., 'exact variant/channel SKU'). This goes beyond mere safety flags, although it does not discuss pagination or rate limits—but the output schema and limit/offset parameters handle that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, each earning its place. The first defines what the tool returns and the domain; the second lists the filter dimensions. No filler, no repetition of schema details, and the key information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.