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

With no annotations, the description carries full burden. It reveals key behaviors: source distinction, soft-delete exclusion, and price attachment. However, it does not clarify whether multiple identifiers can be combined, ordering of results, or other side effects.

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

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

The description is three sentences long, front-loaded with the main purpose, and provides essential contextual information without extraneous details. 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 9 parameters, no annotations, and no output schema, the description covers primary lookup behavior and key filters but omits details on limit, env, result format, and error handling. Adequate but has clear 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?

Schema description coverage is low (22%); the description adds meaning for sku, htsCode, shopifyProductId, bpProductId, title, source, and includeRemoved. However, it omits limit and env, and does not explain each parameter's constraints beyond the schema defaults.

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 'Look up commodities' with a specific action and resource. It lists exact identifiers (sku, htsCode, etc.) and distinguishes from sibling tools, which are all different operations (e.g., coverage_report, db_query).

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 explains the context of ERP vs. manual rows and soft-deletion, but does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. Since no sibling is a lookup tool, the guidance is sufficient but not explicit.

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

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

The description explicitly states it is 'Read-only' and 'flags are recomputed live', providing key behavioral traits. With no annotations provided, this is valuable. It does not cover rate limits or pagination, but the mutation safety is well conveyed.

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

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

The description is three sentences with no fluff. It front-loads the core purpose and includes essential context (read-only, live recompute, defaults). Every sentence 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 no output schema, the description does not explain the return format (e.g., fields, count, pagination). It also lacks details on ordering or behavior with zero results. While the purpose is clear, the lack of output structure hinders full comprehension.

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 67% (env and country have descriptions, limit does not). The tool's description adds no parameter information beyond the schema. The undocumented 'limit' parameter leaves a gap for the agent, as its purpose and constraints are not explained.

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' and the resource 'shipping contacts that currently warrant a system status flag', specifying exact conditions. It distinguishes this tool as a read-only counterpart of a backfill script, which differentiates it from sibling tools like db_query or coverage_report.

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 checking contacts that will break FedEx label creation, and notes it is read-only and live-recomputed. However, it does not explicitly state when to use vs. alternatives or provide exclusion criteria, but the context is clear enough for an agent.

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?

No annotations provided, so description must fully explain behavior. It omits side effects (e.g., destructive?) and doesn't clarify 'acknowledge' meaning. Lacks safety or side-effect details.

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 core purpose, no waste. Efficient and to the point.

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?

Describes return concept (ADDED/REMOVED) but lacks specifics on format, pagination, or examples. Adequate for a simple tool but missing details for full completeness.

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

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

Schema already covers the single param 'env' with description. The tool description does not add further meaning beyond schema, so baseline 3 is appropriate.

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

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

The description clearly states it diffs live schema against baseline snapshot, explaining ADDED/REMOVED items. It uniquely identifies the tool's purpose among 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?

Mentions running 'npm run snapshot' to acknowledge, but doesn't explicitly compare to siblings like schema_check or state when not to use. Usage context is implied, not 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?

With no annotations provided, the description carries the full burden. It clearly states the tool is read-only, allows only specific SQL statement types, and is single-statement. It also hints at the binding syntax. It does not specify error handling or permissions, but the core behavioral trait (read-only) is well communicated.

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

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

Two sentences, front-loaded with the core action and constraints. Every sentence is informative and earns its place. 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?

Given the tool's complexity (direct SQL execution), the description covers the query types allowed, database target, parameter binding, and the escape hatch role. It does not describe the return format (e.g., rows as JSON), which might be assumed. Overall, it is largely complete for the usage context.

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

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

Schema coverage is 100% (3 parameters described), so baseline 3. The description adds value by explaining that parameters are passed as $1,$2,… bind values, which clarifies usage beyond the schema's type definitions. This is a meaningful addition for an AI agent.

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 runs read-only SQL queries (SELECT/WITH/EXPLAIN/SHOW only) against a specific database. It uses a specific verb ('Run') and resource term ('SQL query'), and distinguishes itself from sibling tools by being an 'escape hatch' for queries not covered by curated tools.

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

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

The description explicitly positions the tool as an 'escape hatch' for cases not covered by other tools, providing good context. It also restricts usage to read-only queries. However, it does not explicitly list when not to use it or name specific alternatives, though the sibling list implies the alternatives.

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?

No annotations provided, so description carries full burden. It explains return fields (id, display name, disambiguating context, contact flags, sole) and data source (same as app form). While it doesn't explicitly state read-only or auth requirements, the nature as a list tool is clear and 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?

Description is a single paragraph that front-loads the main purpose, then details return structure and usage. It is fairly concise given the information needed, with 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?

Given no output schema, description compensates by listing return fields. It explains relationship to sibling tools and env parameter default. Lacks pagination or error handling info, but is reasonably complete for a 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 coverage is 100%, but description adds context: env defaults to dev (safe), shipmentType determines sources (contacts for international, stores for domestic). This adds meaning beyond the enum values.

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 ship-from/ship-to/importer parties by name, returning IDs and display info. It distinguishes itself from siblings by specifying it should be called before label_preflight/label_create when party IDs are unknown.

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

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

Explicitly says when to use: 'Call this before creating a label when you don't already have the party IDs.' It also instructs to show names to user and pass the chosen ID to label_preflight/label_create, and indirectly implies not needed if IDs are already known.

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

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

The description explicitly declares zero side effects, which is critical for a validation tool. It enumerates all behavioral aspects: party resolution, contact system flags, commodity checks, unit-value suggestions, declared-value limit, and env wiring. No annotations are provided, so the description carries the full burden, and it does so thoroughly.

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, dense sentence that front-loads the key purpose ('Validate... with ZERO side effects') and then lists checks. While it conveys all information, the structure is somewhat run-on and could benefit from bullet points for readability. Still, it is appropriately sized and contains 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?

The description thoroughly covers what the tool does but omits any mention of output or return value. Since there is no output schema, the description should indicate what the tool returns (e.g., validation errors, summary). This gap reduces completeness given the tool's complexity (11 parameters, detailed checks).

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 high (82%), but the description adds meaningful context beyond schema definitions. It explains preflight's role in suggesting values (e.g., unitValue, commodity fields) and clarifies behavior for custom lines (no unit-value suggestion). This enhances understanding of parameter semantics during validation.

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 validates a FedEx shipment with zero side effects, listing specific checks (party resolution, commodity validation, unit-value suggestions, declared-value limit). It positions itself as a pre-validation step ('Run this first'), distinguishing it from any creation tool. The purpose is unambiguous and specific.

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

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

The description explicitly recommends using this tool first ('Run this first'), implying it should precede label creation. It also notes that custom lines have different handling (no unit-value suggestion). However, it does not explicitly state when not to use it or contrast with siblings like label_options, leaving some ambiguity about alternatives.

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?

No annotations exist, so the description bears full burden. It discloses it reports missing dependencies and uses 'ok:true' for contract check, but does not reveal if the operation is read-only or has side effects, nor any auth or rate limit info.

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

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

Description is two sentences with no waste, clearly stating purpose and output meaning. Could be slightly more structured for readability, but overall concise and front-loaded.

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

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

The description is adequate for a tool with one simple parameter, but lacks details on output format (no output schema). It mentions 'ok:true' but not the structure of the report, which is a gap for the 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 one parameter fully described in the schema (env with enum and default). The tool description adds no further meaning beyond what the schema provides, so baseline score 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 introspects the live DB to report missing tables/columns that tools depend on, which is a specific verb+resource purpose. It distinguishes from siblings like 'db_query' or 'coverage_report' by focusing on contract drift breakage.

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. No explicit context for usage, such as prerequisites, when to check drift, or when to prefer other tools like 'db_query'.

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

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

With no annotations, the description carries the full burden. It discloses what the tool returns (summary, files, raw request, etc.) and explains the 'allReady' flag and batchId behavior. However, it does not explicitly state whether the tool is read-only or has side effects.

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

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

The description is three sentences, front-loading the purpose and efficiently covering key points without wasted words.

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

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

Given 4 parameters, no output schema, and no annotations, the description thoroughly explains the tool's return structure and behavior, including the summary fields, files list, raw request, and 'allReady' flag, providing sufficient context 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 only 25%, but the description adds meaning by specifying that 'transactionId' is FedEx-specific and 'batchId' is a uuid. It does not mention the 'env' parameter, but overall it compensates for the schema's lack of detail.

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 provides a '360° rollup for ONE tracking request' by specific identifiers, distinguishing it from listing tools like 'tracking_requests_list'. It specifies the verb 'rollup' and resource 'tracking request'.

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 includes a usage hint: 'use this after creating a label to show the summary and files.' It implies when to use but does not explicitly state when not to or name alternatives, though the context of sibling tools makes the distinction 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?

No annotations exist, so the description carries full burden. It discloses that missingTrackingOnly surfaces requests without tracking_number due to a fire-and-forget webhook, and that soft-deleted rows are excluded by default. It does not discuss mutation safety, rate limits, or other behavioral traits, leaving gaps.

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

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

Two sentences plus a short note, all front-loaded with key information. Every sentence earns its place with no fluff. Very concise yet informative.

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

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

Given 7 parameters, no output schema, and no annotations, the description covers key filtering intentions but omits details on sorting, pagination (limit), and other filters. It is adequate for basic use but not fully complete for a parameter-heavy 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 low (29%), so the description should compensate. It explains the purpose of missingTrackingOnly and imply includeDeleted behavior. However, other parameters (env, limit, status, batchId, shipmentType) are not addressed, leaving them underspecified. The description adds value for two params but not enough to fully 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 tracking requests with triage filters, specifying the resource and action. It provides specific details about missingTrackingOnly and includeDeleted, making the purpose clear. However, it does not explicitly distinguish from siblings like tracking_request_overview, so loses some points.

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

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

The description gives context on when to use missingTrackingOnly (for stuck requests) and mentions soft-deleted exclusion. However, no guidance on when to use this tool versus siblings (e.g., tracking_request_overview, db_query) or alternatives. It provides some usage hints but lacks comparative guidance.

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