zobrx

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

Annotations already declare readOnlyHint=true, so the description adds value by explaining the return content ('document text for ChatGPT deep research'). No contradictions.

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, no wasted words. Essential information is front-loaded: action, resource, and output purpose. Ideal conciseness.

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 only one parameter, no output schema, and annotations present, the description covers purpose, usage, and output sufficiently. Simple tool requires no more.

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 parameter, and the description largely repeats the schema's description. It adds the example prefix 'product:' and ties it to search, but minimally expands meaning 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 clearly states the verb 'Fetch' and the resource 'full detail of a result returned by search', distinguishing it from sibling tools like get_account_profile or search. It specifies the exact use case and output type.

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 after running search, and provides an example ID format. However, it does not explicitly state when not to use it or mention alternatives, but the sibling structure makes this 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, so the description's statement that it returns user and corporate profile details is consistent but adds limited additional behavioral context beyond listing fields.

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 efficiently communicates the tool's purpose 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?

For a simple, parameterless read tool with no output schema, the description adequately covers what the tool returns, though it could mention authentication requirements or rate 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?

There are zero parameters, so the description does not need to add parameter semantics. Baseline of 4 is appropriate as it provides no misleading 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 states the tool returns 'workspace profile' including user details and corporate/tenant profile with specific fields (legal name, tax IDs, etc.), which distinguishes it from sibling tools like get_orders_summary or get_analytics_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 the tool should be used to retrieve workspace profile information, but provides no explicit guidance on when to use it versus alternatives, nor any conditions 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 readOnlyHint=true, so the description reinforces a read operation. It adds value by listing the specific data fields returned, beyond what annotations provide. No contradictions.

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, efficient sentence that lists all key information without extraneous words. It is front-loaded with the main concept.

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 description lists the returned fields, which is sufficient for a simple wallet query with no parameters and no output schema. It could mention the output format, but the list is fairly 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 has no parameters (coverage 100%), so the description is not required to explain parameters. Instead, it clarifies the output contents, adding meaning beyond the empty schema. Baseline 4 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 providing AI spend wallet details including balance, month-to-date spend, monthly cap, auto-recharge status, and last top-up. This specific resource distinguishes it from siblings like get_account_profile or get_inventory.

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 AI wallet information is needed, but provides no explicit guidance on when not to use it or alternatives. No explicit exclusions or context 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?

Annotations already declare readOnlyHint=true. The description does not contradict and adds the specific metrics returned, but does not disclose any additional behavioral traits beyond what annotations provide.

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 efficiently communicates the tool's purpose. It is front-loaded and concise, with no unnecessary 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 parameter, no output schema), the description covers the basic metrics. However, it could be more complete by adding context like data freshness, timezone assumptions, or how metrics are defined.

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 the sole parameter (range) with enum values and description. The tool description adds no extra parameter information, so it meets the baseline for high 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 states it returns a GA4 summary with specific metrics (sessions, users, conversions, etc.). However, it does not explicitly distinguish from sibling tools like get_dashboard_summary or get_marketing_summary, which could overlap.

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, nor any context for when not to use it. It only lists what data it returns.

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. Description adds specific items returned but does not elaborate on behavior (e.g., empty state). 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?

Single sentence, no wasted words, front-loaded with key terms.

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 no parameters, no output schema, and read-only annotations, description sufficiently covers what is returned.

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?

No parameters; description adds value by enumerating return fields. Baseline 4 for zero 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?

Description clearly lists specific components of brand identity: logo, colors, fonts, etc. Distinguishes from sibling get_brand_score which is about brand performance.

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. Does not mention any conditions 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 readOnlyHint=true. The description adds behavioral context: it returns the latest day's score (not historical), and includes listing count coverage. This goes beyond annotations without 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?

Single sentence with efficient structure: states the purpose, composition, and return value. No 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?

With zero parameters and no output schema, the description covers the core return values (score and listing count). However, it could be more precise about the data type and structure of the score.

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?

No parameters exist, so baseline is 4. The description doesn't need to add parameter details, and it properly explains what the tool returns in the absence of an output 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 it retrieves the latest brand-health score, a weighted average across specific marketplace metrics. It distinguishes itself from other 'get' tools by specifying the exact resource and its components.

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 retrieving a workspace's brand score but does not explicitly differentiate from sibling tools like get_brand_pack or get_analytics_summary. No when-not or alternative 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?

Annotations already declare readOnlyHint=true. The description adds context by specifying it returns synced order counts per channel for specific marketplaces, which is useful beyond the annotation. 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, front-loaded with the purpose. Every sentence earns its place—first sentence states what it returns, second sentence adds use case. No fluff.

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 tool with no parameters and no output schema, the description fully explains what it returns and for which marketplaces. It is complete given the tool's simplicity.

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 has 0 parameters, so description coverage is 100%. The description adds meaning by explaining the output (order count per channel), which is valuable since the schema alone provides no 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 states the tool returns order volume across non-Amazon marketplaces, listing specific channels. It distinguishes itself from siblings like get_orders_summary by specifying non-Amazon and per-channel scale.

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 explicitly says 'use it to see which marketplaces have data and their relative scale,' providing clear context. It does not mention when not to use or alternatives, but the use case is well-defined.

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 readOnlyHint=true and openWorldHint=false. Description adds value by detailing the data content (counts, breakdown, recent violations) beyond 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 sentence, no wasted words, front-loaded with key terms 'Minimum-advertised-price / MRP compliance violations'.

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 0-parameter, no-output-schema tool, description adequately explains what it returns. Could mention output format but not critical 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?

No parameters, schema coverage 100%. Baseline 4 applies; description adds no param info but none 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?

Description clearly states it provides MAP/MRP compliance violation data: open + escalated counts, channel breakdown, and recent violations. Specific verb+resource distinguishes it from other get_* tools like get_analytics_summary or get_inventory.

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?

Clear context: for compliance violation reporting. No explicit when-not or alternative tools, but the domain specificity makes usage obvious among many generic get_* 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 openWorldHint=false, so the description mainly adds context about the content (integrations by status, recent activity). It does not discuss behavioral traits like caching or real-time data, but 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?

Two sentences: first describes output, second gives usage guidance. No unnecessary words, front-loaded with key 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 zero-parameter, read-only tool with no output schema, the description covers purpose, content, and usage context fully. It is complete and leaves no 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?

With zero parameters, schema coverage is 100%. Per guidelines, baseline is 4. The description doesn't need to add parameter info, and it doesn't.

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', providing a specific verb and resource. It distinguishes itself from sibling tools like get_analytics_summary by focusing on integrations and account activity.

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 advises 'Use this first to answer how is my business set up / what's connected', giving clear context for when to use this tool. While it doesn't explicitly list alternatives or when not to use it, the guidance is strong.

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. Description adds specific outputs but lacks details like data freshness or pagination. 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?

Single sentence, front-loaded with key information, no 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?

Covers main outputs (buckets, fee, actions) adequately for a simple read-only tool. Could mention scope (global vs. per-marketplace) but 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?

No parameters; schema coverage is 100%. Description adds no param info but 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?

Description clearly states it's about Amazon FBA inventory health with specific components (aging buckets, storage-fee exposure, actions). Differentiates from sibling tools like get_inventory and get_orders_summary by focusing on health metrics.

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 when-to-use or alternative guidance. Implied usage for FBA health but unclear when to use vs. get_inventory or other inventory 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 indicate readOnlyHint=true. The description adds behavioral context by specifying the data included (section totals and HSN rollup) without contradicting 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 sentence, no waste, front-loaded with key information: GSTR-1 outward-supply summary for a period.

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, the description covers the purpose and expected output (section totals and HSN rollup) sufficiently, though no output schema is provided.

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 period parameter having description and enum values. The description mentions 'for a period' but adds no further detail beyond schema, so 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, listing specific sections (B2B, B2CL, B2CS) and HSN-wise rollup for return preparation, which distinguishes it from sibling tools like get_hsn_summary or get_tax_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 use for return preparation but does not explicitly state when not to use or mention alternatives among sibling tools like get_hsn_summary or get_tax_summary.

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, so the description does not need to reiterate safety. It adds value by disclosing the data returned (taxable value, taxes, invoice count) and the aggregation level (per HSN code). 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?

The description is a single, concise sentence that front-loads the key action and includes essential details. Every word serves a purpose, with no redundancy or irrelevant 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?

Given the tool's low complexity (one optional parameter, no nested objects, no output schema), the description is largely complete. It specifies what data is returned. However, it could clarify whether the output is a list of HSN codes or a single aggregated object. A minor gap.

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 parameter 'period' is fully described in the input schema (enum values and description) with 100% coverage. The tool description only mentions 'for a period' in passing, adding no extra meaning beyond the schema. 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 the tool's purpose: 'Per-HSN-code tax rollup (taxable value, CGST/SGST/IGST/cess, invoice count) for a period.' It specifies the verb 'rollup' and the resource 'HSN code tax data', distinguishing it from sibling tools like get_gstr1_summary or get_tax_summary that cover different tax scopes.

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 per-HSN tax summaries but does not explicitly state when to use this tool over alternatives (e.g., get_tax_summary, get_gstr1_summary). No exclusions or prerequisite conditions are provided, leaving the agent to infer context from sibling names.

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 readOnlyHint=true, so the description adds value by specifying the join behavior and the row limit. It does not contradict annotations and provides useful behavioral context beyond what annotations offer.

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 purpose, then constraints. Every word earns its place with no redundancy or fluff.

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 is read-only with two optional params and no output schema, the description covers the key aspects: returned data, optional search, and row limit. Minor gaps like pagination or error handling are acceptable for this simplicity.

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% and both parameters have descriptions. The description adds minimal extra meaning by reiterating the free-text search and limit behavior. Baseline 3 is appropriate as the description does not significantly enhance parameter understanding 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 it retrieves warehouse stock levels by SKU including available, reserved, incoming, blocked, joined with product details (name, cost, MRP). It distinguishes itself from sibling tools by specifying the exact data returned.

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 what the tool returns and that it supports optional free-text search by SKU with a row limit of 25. It does not explicitly mention when not to use or alternatives, but the context is sufficient for basic decision-making.

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. The description adds a row limit of 25 and the 'optionally per channel' behavior, but does not clarify how per-channel filtering works or if any side effects occur. Additional transparency about auth or data freshness would help.

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, clear sentence that conveys purpose, data types, and limit. It is front-loaded and concise, though slightly more structure (e.g., separating features) could improve readability.

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 optional parameter, good annotations, and no output schema, the description adequately covers the return values, row limit, and context (P&L). It lacks details on pagination but is sufficient for an agent.

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 limit parameter fully described in the schema. The description confirms the max of 25 rows but adds no new semantic detail beyond the schema for 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 clearly states the tool retrieves per-product margin configuration for P&L, specifying COGS and platform-fee percentage, with optional per-channel granularity. It distinguishes itself from sibling tools like get_pnl_summary by focusing on margin 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 implies usage for P&L analysis but does not explicitly state when to use this tool versus alternatives or provide exclusions. Sibling tools exist for financial data, but no comparative guidance is 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 openWorldHint=false. The description adds value by disclosing that the response includes prior-period deltas and per-platform breakdowns, which are behavioral details beyond the annotations. No contradictions.

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 a lot of detail without extraneous words. It is efficient but could be better structured for readability, perhaps by breaking into shorter phrases.

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 tool with one parameter and no output schema, the description covers the main return values (metrics, deltas, platform breakdown) adequately. It lacks mention of any pagination or additional filters, but given the simplicity, it is largely 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 already fully describes the only parameter (range) with enum values and a description. The tool description does not add any new semantic information beyond restating the window options. With 100% schema coverage, 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 the verb (get), resource (marketing summary), and scope: cross-platform ad performance with specific metrics, prior-period deltas, and per-platform breakdown. It distinguishes itself from siblings like get_analytics_summary by focusing on ad metrics.

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 ad performance queries over a window, but does not explicitly state when to use this vs alternative tools like get_analytics_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 openWorldHint=false, so the description does not need to reiterate read-only behavior. It adds value by detailing the output: counts by type/severity and recent events, and the window parameter. 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?

A single, well-structured sentence that front-loads the purpose and efficiently conveys the tool's functionality (window, counts, events). 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 the simple parameter set and the presence of annotations, the description adequately covers what the tool does and what it returns. Lack of output schema is mitigated by explaining the result shape (counts and events). Sufficient for the tool's 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 only parameter (days) has 100% schema coverage with a clear description. The description's mention of 'in a window' aligns with the parameter but does not add new semantic meaning beyond the schema's definition. 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 the tool retrieves marketplace alert events (price drops, OOS, etc.) within a window, providing counts by type and severity plus the most recent events. This specific verb-resource pair distinguishes it from siblings like get_orders_summary or get_inventory.

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 querying marketplace alerts but does not explicitly state when to use this tool versus alternatives. No exclusion criteria or alternative tool names are provided, leaving the agent to infer context from sibling names.

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, so the description adds value by specifying the content (severity, title, state). It does not contradict annotations and provides context 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?

Single sentence that is front-loaded with the key concept 'In-app notifications inbox' followed by specific fields. No unnecessary words, every part 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?

Given zero parameters and no output schema, the description is complete: it states the tool returns recent alerts with three specific fields. This is sufficient for an agent to understand 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 has no parameters, so no parameter information is needed. The description clearly explains what the tool does without relying on 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?

Description clearly states the tool returns an inbox of recent notifications with severity, title, and state. It differentiates from sibling tools like get_orders_summary or get_analytics_summary by specifying the exact resource and 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 usage for viewing notifications but does not explicitly state when to use or avoid this tool versus alternatives like get_analytics_summary or get_compliance_violations. No exclusions or prerequisites 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 mark the tool as read-only. Description adds context about aggregation across channels and marketplaces but does not detail auth requirements, rate limits, or any side effects. With annotations, the added value is moderate.

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 zero waste. First sentence states the core function, second provides use context. Front-loaded and 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?

With no output schema, description explains the output is order volume per channel, but lacks detail on structure (e.g., channel names, volume format). Single parameter is well-covered. Adequate for a simple aggregated 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?

Schema description coverage is 100%. The only parameter 'days' is fully documented in the schema. Description does not add additional detail beyond what the schema provides, so baseline score 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?

Description clearly states it provides 'Order volume per channel over a window, across all connected marketplaces.' This specifies the verb (get/order volume), resource (orders per channel), and scope (all marketplaces), distinguishing it from siblings like get_channel_orders_overview.

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?

Explicit usage guidance: 'Use it to see where orders are coming from and the relative scale per channel.' This provides clear context but no explicit when-not-to-use or alternative 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 indicate readOnlyHint=true, so the description's addition of output metrics adds some context. However, it does not disclose behavioral details such as required permissions, rate limits, or the meaning of 'major units'.

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, no redundancy, front-loaded with the key outcome. 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 1-parameter tool with no output schema, the description provides the main outputs but omits details like output structure (single object vs. per-channel list) and the unit for the net amount.

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% and the parameter 'days' is described in the schema. The description only implicitly references the time window, adding no new 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 returns the net settlement amount and count of records per channel, distinguishing it from other summary tools by specifying the exact metrics and aggregation level.

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 usage guidance is provided. The description does not indicate when to use this tool versus alternative summary tools like get_orders_summary or get_pnl_summary, making selection ambiguous.

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, so the tool is known to be read-only. The description adds that it is Amazon settlement-based and amounts are in major currency units, which is useful context but does not disclose additional behavioral traits (e.g., authentication needs, rate limits). With annotations present, the description is adequate but not exceptional.

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 all relevant details (revenue, fees, refunds, TCS/TDS, net amounts, FBA reimbursements, net to seller, counts). While somewhat dense, it is efficient and front-loaded. Could be improved with structuring (e.g., bullet points) but is well under the character limit.

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 is a simple read-only report with one parameter and no output schema, the description adequately covers what is returned (monetary breakdown and counts) and the context (Amazon settlement-based, major currency units). It is sufficiently complete for an agent to understand the output.

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 a lookback window. The description reiterates 'over a window' without adding new meaning beyond the schema. 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 title 'Get P&L / money summary' and description clearly state it provides an Amazon settlement-based money summary over a window, listing specific components (revenue, fees, refunds, TCS/TDS, net amounts, counts). This distinguishes it from sibling tools that focus on narrower aspects (e.g., get_orders_summary, 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 indicates it covers a time window via the 'days' parameter but does not explicitly state when to use this tool versus alternatives like get_orders_summary or get_payments_summary. The context is clear but lacks explicit guidance on exclusions or preferred 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 the description adds the requirement of a subscription and clarifies that data is from quick-commerce shelf intelligence. However, it does not disclose data freshness, caching behavior, or whether the movers are computed in real-time. The description adds moderate value beyond 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 immediately states the core purpose. Every part serves a function, with no redundant information. It is appropriately 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?

Given the tool's simplicity (2 optional params, no output schema) and that annotations provide readOnlyHint, the description covers the essential context: what PSL movers are, data source, window, and subscription requirement. It could briefly hint at output format but is complete for this 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?

Schema coverage is 100% with both parameters (days, limit) already described in the input schema. The description mentions 'over a window' which loosely maps to days but adds no new semantics beyond the schema. 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 retrieves top potential-sales-loss movers from quick-commerce shelf intelligence, specifying the resource (PSL movers), action (get), and context (window, by channel). It distinguishes from siblings like get_shelf_availability by focusing on loss estimation rather than simple 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 mentions the prerequisite of a Q-Radar subscription but does not provide guidance on when to use this tool versus alternatives like get_shelf_availability or other analytics tools. There is no explicit when-not-to-use or comparison to 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, so the read-only nature is known. The description adds no additional behavioral context such as data freshness, pagination, or auth requirements. It is adequate but not enhanced beyond 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 sentence that efficiently states the tool's purpose and outputs. No filler 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 summary tool with one parameter and no output schema, the description covers key return fields. Minor ambiguity remains about the monetary unit and the count of top reasons, but overall it 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?

The schema covers the single parameter 'days' with a description, so the description adds no new semantic meaning. Baseline 3 is appropriate since schema already handles parameter documentation.

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 the resource (Amazon FBA reimbursements), the aggregation window, and the exact output fields (total amount, count, units, top reasons). This clearly distinguishes it from sibling tools like get_returns_summary or get_payments_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 retrieving reimbursement summaries, but does not explicitly state when to use this tool over alternatives or provide exclusions. No guidance on prerequisites or context is 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description's behavioral disclosure is minimal. It adds context about output composition (count, units, top reasons) but does not add significant behavioral traits beyond 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-worded sentence of 15 words with no unnecessary information. It is front-loaded with the core action and 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?

For a simple summary tool with one optional parameter and no output schema, the description adequately covers the return content and window. Could mention default lookback or that it's specific to Amazon, but overall 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?

Schema description coverage is 100% (days parameter fully described). The description does not add additional parameter semantics beyond what the schema provides, 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 returns an Amazon returns summary over a window, including total count, units, top reasons, and dispositions. It uses specific verbs and resource references, and distinguishes from siblings like get_orders_summary which focuses on orders.

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 vs alternatives (e.g., detailed return queries). The description implies use for high-level summary but does not mention exclusions or context for choosing this over sibling 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, so no contradiction. Description adds context that it's a 'summary' and lists returned metrics, which clarifies behavior beyond 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?

Extremely concise: two sentences, no fluff. Key information (source, metrics, prerequisite) 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?

Given no output schema, the description adequately explains what data is returned (metrics and top queries). The prerequisite (SEO module) is noted. Could specify result limits or pagination, but not essential for this type of summary.

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% and the schema description for 'range' is clear. The tool description adds little new information about the parameter beyond restating 'window'.

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?

Clearly states it retrieves a Google Search Console summary of top search queries with specific metrics (impressions, clicks, position, CTR). Distinguishes from sibling 'get_serp_keywords' by focusing on GSC data and explicit metrics.

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?

Mentions prerequisite 'Requires the SEO module' and that it operates over a time window. However, no explicit guidance on when to use this vs alternatives like 'get_serp_keywords'.

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, so the safety is covered. The description adds no extra behavioral context beyond stating the module requirement. No contradictions.

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 with no wasted words, efficiently stating purpose and a prerequisite.

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 no output schema, the description lists returned fields (rankings, volume, intent, trend). It lacks mention of pagination or output format but is fairly complete for a simple retrieval tool with one optional parameter.

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 the single parameter 'search', which is described as a free-text keyword filter. The description does not add additional semantic meaning 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 returns tracked SEO keywords with specific fields (current rankings, search volume, intent, rank trend). It also mentions the SERP module requirement, distinguishing it from sibling tools like get_seo_queries.

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 users with the SERP module but does not explicitly state when to use this tool versus alternatives. No exclusion or when-not 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?

Annotations already mark the tool as read-only (readOnlyHint=true) and closed-world (openWorldHint=false). The description adds behavioral context: explains what the metric means (share of observed shelves in stock) and that lower is worse, which is useful for agent interpretation. No contradictions.

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 extremely concise: two sentences, no wasted words. It front-loads the core purpose and metric interpretation, then adds the prerequisite. Every sentence 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?

Given no output schema, the description compensates by explaining the output (OSA% per channel for last 7 days) and its interpretation. It provides enough context for an agent to use the tool, though a note about the output format would be nice but not essential given simplicity.

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 no parameters (schema coverage 100% by definition), so the description does not need to explain any. Baseline 4 applies as the description adds no parameter information, but none 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 states the tool retrieves quick-commerce on-shelf availability (OSA%) over the last 7 days per channel. It defines the metric and distinguishes it from sibling tools by specifying a unique domain (quick-commerce) and subscription requirement (Q-Radar).

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: the metric is over last 7 days per channel, with interpretation guidance (lower is worse). It explicitly states the prerequisite (Q-Radar subscription). While it doesn't list alternatives, the context is sufficient for an agent to understand when to use this 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. Description adds context about the specific tax fields returned (CGST/SGST/IGST, inter/intra-state) but does not disclose any additional behavioral traits such as authorization needs, rate limits, or response size. Adequate but not exceptional.

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 sentence, perfectly front-loaded with core purpose, zero wasted words. Achieves maximum information density.

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 low-complexity tool (1 optional enum param, no output schema, read-only), the description adequately covers the returned fields (taxable value, taxes, invoice count, state types). Could optionally mention return format or pagination, but not essential.

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 parameter (period) with a clear enum and description. Description adds 'for a period' which reinforces but does not extend the schema detail. Baseline 3 is appropriate as schema already documents the parameter well.

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 states verb 'get' and specific resource 'state-wise tax breakdown', enumerating exact fields (taxable value, CGST/SGST/IGST, invoice count, inter/intra-state). Unambiguously distinguishes from sibling tools like get_tax_summary or get_gstr1_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?

No guidance on when to use this tool versus alternatives (e.g., get_tax_summary, get_gstr1_summary). Does not mention prerequisites, exclusions, or typical use cases. Only implies use 'for a period'.

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, so the description is not required to repeat safety details. It adds value by specifying the output structure (total, count, breakdown, sample) but does not disclose any behavioral traits like data freshness, pagination, or access scope.

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 purpose and lists all output components without superfluous words. Every part 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 zero parameters, no output schema, and read-only annotations, the description covers the essential outputs. However, it lacks details on the sample size limit or definition of 'tracked marketplace listings', leaving minor ambiguity for complex use cases.

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 description need not explain inputs. It adds meaning by detailing what the tool returns, fulfilling the expectation for a parameterless tool. Baseline 4 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 'Get' and resource 'marketplace stock status', clearly distinguishing it from sibling tools like get_inventory or get_shelf_availability. It enumerates the output components: total listings, OOS count, breakdown by channel, and sample OOS listings.

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 out-of-stock analysis but does not explicitly state when to use this tool versus alternatives (e.g., get_inventory for full stock levels). No when-not-to-use guidance or alternative references are 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?

Annotations declare readOnlyHint=true, consistent with a read operation. The description adds behavioral context about default state and output fields. No contradictions; could mention response format more fully.

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 sentence packs purpose, scope, and key details. No fluff.

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 parameter and no output schema, the description is appropriately complete. It covers what the tool returns and default filtering. Minor missing details like pagination or response size 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 provides full coverage for the 'state' parameter with enum values. The description adds value by noting default behavior ('Defaults to open items'), which isn't in the schema description.

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 what the tool does: retrieves lines where stored tax doesn't equal rate times taxable value, with per-line drift amounts and workflow state. It distinguishes itself from sibling get_* tools by focusing on tax mismatches.

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 it defaults to open items, hinting at common use. However, it lacks explicit guidance on when not to use this tool or alternatives like get_tax_summary or get_state_wise_tax.

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 readOnlyHint=true, so the description's mention of returning a snapshot without modification is consistent. It adds valuable behavioral context: the specific data fields (tax breakdown, splits, TCS/TDS per channel) and regional scope (India GST), going 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, well-structured sentence that front-loads the key purpose and comprehensively lists the output components without extraneous words. Every detail 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?

Despite lacking an output schema, the description fully explains the return data: taxable value, tax components, invoice count with B2B/B2C split, and TCS/TDS per channel. It also notes the regional context (India GST), making the tool's purpose and output clear for an AI agent.

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 covers the single parameter 'period' with 100% description coverage, listing valid enum values. The description does not add any additional meaning or usage details beyond what the schema provides, warranting a baseline score of 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 states the tool returns a GST snapshot with specific tax components (taxable value, CGST/SGST/IGST/cess, total tax, invoice count with B2B/B2C split, TCS/TDS per channel) for India GST. This distinguishes it from siblings like get_gstr1_summary or get_state_wise_tax by focusing on a period-based 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 obtaining a GST summary for a given period but does not explicitly state when to use this tool over alternatives like get_gstr1_summary or get_tax_mismatches. No exclusion criteria or cross-references are 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?

Annotations already declare readOnlyHint=true, so description doesn't need to restate. Description adds that it returns spend, conversions, ROAS, status per campaign and requires a reporting window. No contradictions.

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, no unnecessary words. Efficiently conveys purpose and key 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 two simple parameters and no output schema, the description adequately covers what the tool does and returns. It mentions module requirement and performance metrics. Could be slightly more explicit about default behavior, but 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?

Schema has 100% coverage with clear descriptions for range and platform. Description does not add additional parameter meaning; it mentions output metrics which are not parameters. 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?

Description clearly states it lists ad campaigns with per-campaign performance metrics. Verb 'list' and resource 'campaigns' are specific. Distinguishes from sibling summary tools by indicating it returns performance data per campaign.

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?

Mentions 'Requires the campaigns module' as a prerequisite but does not provide explicit guidance on when to use this tool versus alternatives like get_marketing_summary or fetch. Usage context is implied but lacks 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 description adds context about default state ('open by default') and contents (severity, action plans). This adds value beyond annotations without 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?

Single sentence that front-loads key information 'AI Coach recommendations inbox' with no wasted words. 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 tool with one optional parameter and no output schema, the description covers purpose and basic behavior. Lacks detail on return format or pagination but is largely complete given tool simplicity.

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 one parameter described in schema. Description reinforces default value for 'state' but adds no new semantic information beyond what the schema provides.

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 states the tool lists AI Coach recommendations (issues/opportunities) with severity, state, and action plans. Name and title reinforce the resource and verb, distinguishing it from singular get_* siblings.

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?

Description implies use for viewing recommendations inbox but offers no explicit guidance on when to use this tool versus alternatives like get_compliance_violations or get_marketplace_alerts, nor when not to use it.

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 the description adds that the list is operator-curated and includes priority/status. However, it doesn't disclose ordering, pagination, or default behavior beyond the basic 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?

Single sentence, front-loaded with key information. Efficient but could be slightly more descriptive without adding clutter.

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 no parameters, annotations, and no output schema, the description adequately explains the output (list of competitors with priority and status). Lacks details like sorting or empty list behavior, but sufficient for a simple read-only 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?

No parameters present, and schema coverage is 100%. The description adds meaning about the output content, fulfilling the baseline for zero-parameter tools.

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 operator-curated competitors with priority and status, distinguishing it from sibling tools that list other entities like sellers or stores.

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 vs alternatives, but as a simple list tool with no parameters, usage is straightforward. Lacks exclusions or context about when not to use.

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 operation, and the description adds that it returns connection status, health score, and last sync time, 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?

Single, clear sentence that is front-loaded and contains no unnecessary 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?

The description covers the return fields well, and given the simple nature of the tool with no parameters or output schema, it is sufficiently complete for an agent to understand the output.

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?

No parameters exist, and schema coverage is 100%, so the description does not need to add parameter details. Baseline score of 4 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 workspace's connected channels and data sources, with specific examples like Amazon and Shopify, and distinguishes from siblings such as list_stores and list_campaigns.

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 provide when-to-use or when-not-to-use guidance compared to sibling tools, though the purpose is clear enough for an agent to infer usage context.

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 readOnlyHint=true, so the description does not need to repeat that. It adds that sellers come with classification and rating from tracked listings, which is helpful but does not elaborate on behavioral traits beyond what annotations provide.

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 followed by the optional filter. It is concise and wastes no words, though a bit more structure could enhance readability.

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 no output schema, the description covers the source (tracked listings) and output (classification and rating). It explains the optional filter and scope. For a simple list tool with two optional parameters, this is fairly 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 schema already describes both parameters with 100% coverage. The description mentions 'optional channel filter', which adds no new semantic meaning beyond the schema description. 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 that the tool lists sellers observed on tracked listings, including their classification and rating. It specifies the scope as the 'competitive seller universe' and mentions an optional channel filter, distinguishing it from similar tools like 'list_competitors'.

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 the tool is for the competitive seller universe and mentions an optional filter, but it does not explicitly state when to use this tool versus alternatives or when not to use it.

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 openWorldHint=false, which the description does not contradict. The description adds context about the returned data (30-day order count) but does not disclose additional behavioral traits such as pagination, rate limits, or whether the data is real-time. It adds moderate value beyond 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, efficient sentence that lists all essential information: action, resource, included fields, and time range. Every word contributes value, and critical details (platform examples, specific fields) are front-loaded for quick understanding.

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 (no parameters, no output schema, clear scope), the description is fully complete. It states exactly what the tool returns and for which entities, leaving no ambiguity about its behavior or output.

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 description cannot add meaning beyond what the schema provides. Schema description coverage is 100%. The description correctly focuses on what the tool returns rather than inputs, meeting the baseline expectation for a parameterless tool.

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 verb 'list', the resource 'connected store/marketplace accounts', and the specific fields returned (display name, country/currency, order count in last 30 days). It lists example platforms, making the scope unambiguous and distinguishing it from sibling 'get_*' tools which return details for a single entity.

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 (e.g., 'get_orders_summary' for order counts per channel). There is no mention of prerequisites, limitations, or situations where another tool 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 declare readOnlyHint=true, indicating safety. The description adds a behavioral constraint: the tool requires 'org member-read permission (Owner/Admin)', which is beyond annotations. No contradictions; the description aligns with read-only nature.

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 states core functionality, second adds permission context. No redundant or wasted words; every sentence 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?

Considering no parameters and minimal annotations, the description sufficiently covers what the tool returns (members with roles/permissions) and its required permissions. Lacks details on output format or pagination, but for a simple list, is mostly 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 has zero parameters and 100% schema coverage. The description adds no parameter details, but with no parameters, baseline of 4 is appropriate. Nothing to compensate.

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 workspace members with their roles and effective permissions, using a specific verb ('list') and a clear resource ('team members'). It distinguishes itself from sibling tools like list_campaigns or list_stores by focusing on membership and permissions.

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 permission prerequisite (org member-read) but offers no guidance on when to use this tool versus sibling tools like fetch or search_catalog. No explicit 'when-not' or alternative suggestions 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?

Description says it returns citeable results with stable ids, adding value beyond the readOnlyHint annotation. No contradictions. Does not disclose any potential side effects, but tool is clearly read-only.

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 states action, second explains output format and usage. No unnecessary words. 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?

For a simple one-parameter search tool with no output schema, the description adequately explains input, output, and integration with 'fetch'. The mention of 'Used by ChatGPT deep research' is an extra touch.

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% and description adds value by specifying the fields searched (title, brand, SKU), which is not in the schema property description.

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 states it searches the product catalogue by free text (title, brand, SKU). Distinguishes from sibling 'fetch' by noting that search returns citeable results with stable ids for later retrieval.

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?

Describes when to use (free-text search) and hints at using 'fetch' for full detail, but does not explicitly differentiate from sibling 'search_catalog', which may serve a similar purpose.

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 readOnlyHint=true, and the description adds behavioral context: returns up to 25 matches, fields (MRP, mapped-channel count, status), and hints at truncation. This adds value beyond 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?

Three sentences, front-loaded with the main action, no fluff. Every sentence provides necessary 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 read-only search tool with no output schema, the description covers return fields, truncation behavior, and scope. Could mention rate limits or pagination, but overall 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 coverage is 100%, but the description adds meaning: explains 'query' matches product title, brand, or SKU, and 'limit' caps results. This goes beyond what the schema alone provides.

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 what the tool does: searches the master product catalog by free text matching title, brand, or SKU, and returns up to 25 matches with specific fields. This distinguishes it from sibling tools like generic search or inventory 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 implies usage with 'Narrow the query if results are truncated,' but lacks explicit guidance on when to use this tool versus alternatives like 'search' or 'get_inventory'. No exclusions or alternative tool names are mentioned.

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