Server Quality Checklist

Tool Scores

• hcp_set_business_profileA
  3.8/5.0
  Behavior1/5

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

  The description contradicts the destructiveHint annotation. It states 'null clears one' section, which is a destructive operation, while annotations declare destructiveHint=false. This is a direct contradiction, and per the rules, transparency is scored 1.

  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?

  Four sentences pack significant information: purpose, replacement/clearing behavior, storage location, and privacy/security constraints. Every clause earns its place, though it could be slightly tightened.

  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?

  The description fully covers the tool's behavior: what it stores, how sections are replaced/cleared, where the profile lives, and what it never contains. For a setter with no output schema, this is comprehensive and equips an agent for safe invocation.

  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?

  The schema already describes all five parameters (100% coverage). The description adds crucial semantics beyond the schema: null clears a section, and vendor's account_hint rejects full account numbers. This enriches parameter understanding.

  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 clearly states the tool's function: 'Store one or more business-profile sections for this installation' and names all five sections. It distinguishes itself from the sibling hcp_get_business_profile by focusing on writing/updating, not reading.

  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?

  It provides a critical usage guideline: 'save a section only after reading the whole section back to the user for a yes.' It does not explicitly name alternatives, but the contrast with hcp_get_business_profile is implicit. The privacy statement also informs when to use.

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

• hcp_api_notesA
  4.7/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds further context by revealing that the tool makes no API call, reads a local compiled table, costs nothing, and cannot fail. This enriches the behavioral profile beyond the annotations without contradicting them.

  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 long but every sentence delivers crucial guidance: purpose, when to call, content of the table, how to phrase queries, and the no-cost/no-fail guarantee. It is front-loaded with the core purpose and structured logically, with no filler.

  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 a single optional parameter, rich annotations, and no required output schema, the description fully explains what the tool does, what it contains, and what to expect. It leaves no significant gaps for an agent to misuse it.

  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 schema already provides a thorough description for the single 'topic' parameter, including examples and the omission rule. The description's mention of 'plain words' is redundant with the schema's guidance. With 100% schema coverage, the description adds no meaningful parameter semantics beyond what the schema already offers.

  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 clearly states the tool's unique purpose: looking up verified behavior of the Housecall Pro API versus its published docs. The verb 'look up' combined with the resource (verified behavior table) distinguishes it from sibling tools like hcp_get_business_profile or hcp_set_business_profile, which make actual API calls.

  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 the tool: before concluding something cannot be done, before retrying a 404, and after a write that appears to have no effect. Also provides alternatives by contrasting with published documentation, making the use cases unmistakable.

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

• hcp_get_business_profileA
  4.7/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds valuable context beyond these: that no data is read from or sent to Housecall Pro or anyone else, that an empty profile is normal for fresh installs, and that sections carry confirmation dates.

  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 three sentences, each earning its place: content overview, usage guidance, and privacy/edge-case behavior. It is front-loaded with the core read action and then provides necessary context without fluff.

  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 no output schema, the description adequately explains return semantics (missing_sections, section dates) and covers data locality and empty-profile handling. It offers a complete mental model for an agent to decide when and how to invoke the tool.

  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?

  The tool has 0 parameters, so the baseline is 4. The description compensates by explaining what the returned structure contains (missing_sections, sections with dates), which is helpful 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.

  Purpose5/5

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

  The description uses a specific verb 'Read' and identifies the resource as 'the business profile stored for this installation', clearly distinguishing it from siblings like hcp_set_business_profile. It enumerates profile contents (pricing rules, payroll rules, etc.), making the tool's purpose unambiguous.

  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?

  The description gives clear context: 'Skills read this before asking setup questions' and explains that missing_sections indicates what a first run still needs to ask. It does not explicitly name alternative tools or state when not to use it, but the occasion is well-defined.

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

• hcp_render_reportA
  4.8/5.0
  Behavior5/5

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

  Annotations already declare the tool read-only, idempotent, and non-destructive; the description adds substantial behavioral detail: output is self-contained/offline, it returns the finished HTML, contract errors are listed and nothing renders, and links are restricted to http/https with specific rendering behavior. This greatly exceeds what annotations alone provide.

  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 long but every sentence is necessary given the complex contract. It is front-loaded with the core purpose, followed by structured contract details, formatting rules, and output behavior. No redundant or filler sentences are present.

  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 complex nested object, sparse schema, and no output schema, the description is exceptionally complete. It covers the full input contract, return value, error behavior, platform-specific handling, security constraints, and rendering nuances, leaving no significant gap for the agent.

  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?

  Although the schema only describes a generic 'report' object, the description fully specifies the contract: required keys (skill, title, sections), section structure (title, severity, blocks), block types (table, prose/lead, list, subhead), optional top-level keys, and markdown formatting rules. This is a comprehensive compensation for the sparse 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?

  The description opens with a specific verb and resource: 'Render a findings report into one self-contained, offline, interactive HTML file.' It also explicitly differentiates from siblings by stating it is a presentation tool that makes no Housecall Pro call and operates on existing findings, making its role unmistakable.

  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?

  The description clearly establishes when to use the tool: when you already have findings and need an interactive HTML report. It also gives platform-specific guidance (write to .html in Claude Code, present as artifact on Claude Desktop). It does not explicitly name alternatives or exclusions, but the context is strong enough to guide appropriate use.

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