pickanagency

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description does not need to repeat safety traits. It adds value by listing return fields and emphasizing read-only nature implicitly. No contradictions; minor gap in explaining that it requires valid slug.

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 plus a usage note, all front-loaded. Every sentence serves a purpose: action, output, when to use, and caution against guessing. 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 get-by-slug tool with one parameter and no output schema, the description sufficiently covers what the tool does, what it returns, and prerequisites (knowing slug from search). The usage note addresses the main ambiguity.

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 'slug' has full schema coverage at 100%. Description adds meaning by defining slug as 'the last path segment of its profile URL' and providing an example. This helps the agent understand the parameter format beyond 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?

Description clearly states 'Fetch a single agency's full profile' and specifies the input (slug) and output fields (description, location, rating, services, website, reviews). It distinguishes from siblings by focusing on a single agency vs search/matching.

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

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

Explicitly states 'WHEN TO USE: after search_agencies or match_agencies...' and warns 'Don't guess slugs - find them via search_agencies first.' Provides clear context for when to invoke 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, destructiveHint=false, and openWorldHint=true, so the description is not required to cover safety. The description adds value by explaining the matching logic (same as free 'Get Matched' tool) and that it returns a ranked shortlist, providing behavioral context 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 concise with three clear sections: what it does, WHEN TO USE, and alternatives. Every sentence adds value, though it could be slightly more streamlined. Overall, efficient and well-structured.

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

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

Given the tool's complexity (matching engine with multiple parameters), the description provides sufficient context: purpose, usage, requirements, and connection to other tools. No output schema exists, but the description states it returns a shortlist, which is adequate. Minor gap: no mention of how results are returned or potential edge cases like no matches.

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 all parameters described. The description briefly mentions 'services needed, location, budget, industry' but does not add new semantic details beyond the schema. Therefore, 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 is a matching engine that returns a ranked shortlist of agencies given a buyer brief. It distinguishes from siblings by naming alternatives for browsing (search_agencies) and drilling down (get_agency).

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 WHEN TO USE section specifies the scenario (user describes needs, wants recommendation) and gives a concrete example. It also clearly states prerequisites (at least one service) and when to use sibling tools instead, providing complete usage guidance.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description adds context about return fields (location, rating, reviews, profile link) and the directory size, enhancing transparency 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?

Well-structured with clear opening, filter list, and usage guide in caps. Slightly verbose but front-loaded and 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 7 parameters all described in schema, no output schema, and annotations present, the description adds directory size, return field details, and usage guidance. Minor omission: no mention of default sort order.

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%, so baseline is 3. Description mentions some filter types but does not add substantial new meaning beyond what the schema already 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 uses specific verb+resource ('Search Pick an Agency's directory') and distinguishes itself from siblings by stating when to use search_agencies vs match_agencies or get_agency.

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

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

Explicitly states 'WHEN TO USE' for browsing/filtering, and contrasts with match_agencies for recommendations and get_agency for specific agency details.

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