Server Quality Checklist

Tool Scores

• get_business_detailsA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It openly states the return payload (opening hours, phones, addresses, reviews, status), the batch limit of 10, and the per-request cost model. While it does not discuss error handling or authentication, it provides significant operational behavior beyond a simple tautology.

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

  Conciseness5/5

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

  Three sentences, each with a distinct purpose: the main action, the return data, and cost/workflow guidance. The description front-loads the primary verb and resource, contains zero filler, and every sentence contributes information.

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

  Completeness5/5

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

  Given that an output schema exists (per context signals), the description already covers the key selection criteria: purpose, input source, limit, cost, and return highlights. It also references sibling tools. For a tool of this complexity, the description is sufficiently complete to guide correct invocation.

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

  Parameters3/5

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

  The input schema already includes a descriptive parameter comment: 'Place IDs from search_businesses or sweep_area,' giving 100% coverage. The tool description adds little new semantic detail beyond repeating 'by place ID' and the max of 10, which is already in the schema. Per the baseline for high schema coverage, a score of 3 is appropriate.

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

  Purpose5/5

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

  The description opens with a specific action: 'Fetch full Google Maps details for up to 10 businesses by place ID.' It clearly names the resource (businesses) and the scope (by place ID, max 10). This distinguishes it from sibling tools like search_businesses, which presumably performs searches rather than fetching details by ID.

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

  Usage Guidelines5/5

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

  The description provides explicit workflow guidance: 'use search_businesses first to narrow the list.' It also gives a cost-based reason ('Costs one API call per place ID') that explains why this tool should be used after narrowing, not as a general search tool. This constitutes clear alternatives and when-to-use guidance.

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

• search_businessesA
  4.6/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries the full burden. It reveals non-obvious behavior: Google ranks by prominence, lacks website/phone suggests last, and the 60-result ceiling can cause truncation. This is valuable context beyond the schema and helps the agent interpret results correctly.

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

  Conciseness5/5

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

  The description is concise and front-loaded: first sentence states purpose, then a compact IMPORTANT block provides essential behavioral warnings. Every sentence adds value without redundancy.

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

  Completeness4/5

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

  For a tool with 6 parameters, nested filters, and an output schema, the description covers the main behavioral pitfall and directs to sweep_area for coverage. It doesn't discuss location/radius interaction, but the schema already documents those fields, and the output schema covers return values. The description is nearly complete for the agent's decision-making.

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

  Parameters3/5

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

  Schema description coverage is 67%, so the baseline is 3. The description adds meaning to the has_website and has_phone filters by explaining their effect on ranking/truncation, and mentions 'lead-qualification filters' generally. However, it does not describe the remaining undocumented parameters (e.g., min_rating, price_levels), so it doesn't fully compensate for the 33% gap.

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

  Purpose5/5

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

  The description states 'Search Google Maps for businesses matching a query, with lead-qualification filters' – a specific verb, resource, and scope. It also mentions sweep_area as a sibling alternative, which distinguishes this tool's purpose from others.

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

  Usage Guidelines5/5

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

  It explicitly says 'Use sweep_area for representative coverage of a city or region', naming an alternative and when to use it. It also provides a key usage caveat about result truncation under has_website:false, helping the agent judge result representativeness.

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

• sweep_areaA
  4.7/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries the full burden. It transparently discloses the tiling algorithm, deduplication behavior, per-tile result ceiling, approximate cost (1-3 API calls per tile), default max_tiles=25, and that every response reports the exact call count. This is far beyond typical descriptions and sets clear expectations.

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

  Conciseness5/5

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

  The description is extremely efficient: four sentences cover purpose, when to use, algorithmic behavior, cost, and defaults. It is front-loaded with the primary action and immediately contrasts with the sibling tool. No redundant or unnecessary wording.

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

  Completeness5/5

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

  Given the tool's complexity (6 parameters, nested filters, an output schema, and sibling tools), the description provides everything an agent needs to decide when to use it, what it does, how it behaves cost-wise, and how to tune it. Since an output schema exists, omitting return value details is acceptable. This is a complete context for task selection and invocation.

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

  Parameters3/5

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

  Schema coverage is around 50%, with descriptions for query, area, filters, and included_type but not for max_tiles or tile_radius_meters. The description adds useful semantics for max_tiles (higher value = better coverage but higher cost) but does not explain tile_radius_meters beyond its name. Baseline 3 is appropriate since the description only partially compensates for the missing schema details.

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

  Purpose5/5

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

  The description opens with a specific verb and resource: 'Search an entire city or region by tiling it into overlapping circular searches, then deduplicating.' It also distinguishes itself from the sibling tool search_businesses by explaining it provides representative coverage rather than top results, making its purpose unmistakable.

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

  Usage Guidelines5/5

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

  Explicitly instructs when to use this tool instead of search_businesses ('Use this instead of search_businesses when you need representative coverage rather than the top results') and explains the underlying difference in result ceilings. Additionally, it gives cost/coverage guidance for max_tiles, helping the agent make informed decisions.

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