Server Quality Checklist

Tool Scores

• measure_roofB
  3.4/5.0
  Behavior2/5

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

  No annotations provided, and the description only lists outputs and args. It does not disclose whether the operation is read-only, requires authentication, has rate limits, or what happens on invalid addresses.

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

  Conciseness4/5

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

  Description is front-loaded with the main action and then details output. It is appropriately sized, though the long list of output fields could be slightly condensed.

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

  Completeness3/5

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

  Given the complexity of roof measurement, the description covers return values well and has an output schema. However, it lacks behavioral context (idempotency, prerequisites, cost) and does not leverage annotations.

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

  Parameters4/5

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

  Schema coverage is 0%, but description fully explains the 'address' parameter: 'Full property address (street, city, state, zip).' This adds necessary meaning beyond the bare schema type.

  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?

  Description clearly states the tool measures a roof from satellite data and lists detailed output. It distinguishes from siblings (generate_roof_report, generate_xactimate_estimate) by focusing on raw measurements rather than reports or estimates.

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

  Usage Guidelines2/5

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

  No explicit guidance on when to use this tool versus alternatives. The description does not mention when to prefer measure_roof over generate_roof_report or generate_xactimate_estimate.

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

• generate_roof_reportA
  3.8/5.0
  Behavior3/5

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

  No annotations provided; description reveals it saves a file and returns path/summary, but lacks details like file location, overwrite behavior, or external dependencies.

  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?

  Two informative sentences plus an args list. No redundant or irrelevant information. Well-structured.

  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?

  Has output schema, so return value description is sufficient. 1 required param, all explained. Minor lack of usage context prevents a 5.

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

  Parameters4/5

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

  Schema coverage is 0%, but description provides clear semantics for all 4 parameters (address, company, contact, phone), including optionality and defaults, adding value over schema.

  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?

  Clearly states verb 'generate', resource 'roof measurement report', format 'Markdown', and return value. Distinct from siblings like 'generate_xactimate_estimate' and 'measure_roof'.

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

  Usage Guidelines2/5

  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 siblings. Does not indicate prerequisites or context for use.

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

• generate_xactimate_estimateA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description must disclose behavior. It reveals that missing required fields triggers a needs_info response, and that defaults are applied for tax_rate, price_list, waste_pct. It also notes the output format (.docx). Missing: description of any side effects or state changes, but the tool is likely read-only for generation. Overall, good coverage.

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

  Conciseness4/5

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

  The description is well-structured: a one-line purpose, followed by a critical note on required fields, then a detailed Args list. Each sentence adds value. It is relatively long (17 parameters explained), but the information density justifies the length. Minor redundancy: some parameter names are repeated, but it remains clear.

  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 17 parameters, no annotations, and presence of output schema (not used for return info), the description covers nearly all aspects: required fields, defaults, optional overrides, integration with measure_roof (measurements_json), and edge case handling. The agent has sufficient information to invoke the tool correctly, including what to ask the user and when to retry.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description must fully compensate. The 'Args:' section explains each parameter in detail: what it is, default behavior, how to obtain values (e.g., 'ask the user'), and dependencies. For example, tax_rate explains researching the rate, price_list explains auto-generation. This adds significant meaning beyond the schema's bare property names.

  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 starts with a clear verb and outcome: 'Generate an Xactimate-style insurance roofing estimate (.docx).' It specifies the output format and distinguishes from siblings (generate_roof_report, measure_roof) by focusing on estimate generation. It also clarifies required fields and edge cases (missing info returns needs_info).

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

  Usage Guidelines4/5

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

  Provides explicit guidance on required fields (homeowner name, date_of_loss) and how to handle missing info (returns needs_info, collect and call again). Mentions optional pre-computed measurements from measure_roof to avoid re-measuring. Could improve by explicitly stating when not to use this tool versus siblings, but the context is clear enough.

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