Server Quality Checklist

Tool Scores

• ha_statusA
  3.5/5.0
  Behavior4/5

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

  Beyond the annotations (readOnly, idempotent, non-destructive), the description explicitly discloses that the tool makes no network calls and avoids sensitive credentials, adding meaningful behavioral context.

  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 brief and direct, using two sentences to convey the essential scope and exclusions without extraneous detail. It is well-structured for quick comprehension.

  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?

  The description explains what the tool does not do and its local-only nature, but it omits details about the expected output or what 'status' encompasses. Given no output schema, this leaves some uncertainty about the return value.

  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?

  With zero parameters and full schema coverage (vacuously), the baseline is 4. There is no parameter description needed, and the description adds no conflicting information.

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

  Purpose3/5

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

  The description states it provides local configuration status, but the exact nature of the status or its output is unspecified. It clearly distinguishes itself from siblings by noting it does not contact Home Assistant, but the core function remains somewhat vague.

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

  Usage Guidelines3/5

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

  The negative statements ('does not read credentials', 'does not contact Home Assistant') implicitly suggest using this tool for local-only status while delegating remote operations to ha_rest or ha_ws, but no explicit when-to-use guidance is provided.

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

• ha_restA
  3.9/5.0
  Behavior4/5

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

  Beyond the annotations (destructiveHint, openWorldHint, etc.), the description adds important behaviors: 'Never retries writes' and 'Responses and duration are bounded'. These are not present in the annotations and provide meaningful operational guarantees. No contradictions with the annotations.

  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 brief and front-loaded, with no redundant or filler content. Each sentence adds value: the core action, path semantics, and key behavioral guarantees.

  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?

  For a generic REST caller, the description provides essential operation and guarantees but lacks guidance on how to structure query parameters or body content. It does not mention error handling, but given the absence of an output schema and the simplicity of the tool, it is reasonably complete, though not fully comprehensive.

  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 only 17% (only allowBinary has a description), but the tool description clarifies the 'path' parameter by explaining it is relative to /api/ with examples. Other parameters like query, body, and contentType remain under-explained in both the schema and description, so the description only partially compensates for the low coverage.

  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 action ('Call a supported method under /api/') and provides concrete path examples ('states', 'services/light/turn_on'). It is easily distinguished from sibling tools ha_status and ha_ws, which are status and websocket-specific.

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

  Usage Guidelines3/5

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

  The description gives usage context by defining paths as relative to /api/ and showing examples, but it does not explicitly compare with sibling tools or state when to use this REST tool versus ha_ws or ha_status. The warning 'Never retries writes' is a behavioral note rather than a usage directive.

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

• ha_wsA
  4/5.0
  Behavior4/5

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

  Annotations already mark destructive/not read-only/non-idempotent; description adds behavior: bridge owns auth/request IDs, optional bounded event collection, socket closes, no retries. No contradiction.

  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 concise sentences; purpose is front-loaded and each clause adds meaningful constraints (auth ownership, bounded collection, socket lifecycle, no retries) without padding.

  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?

  Covers lifecycle and constraints, but omits command format/examples and waitMs semantics; with no output schema it need not describe return values, but the nested command object is underspecified for a correct call.

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

  Parameters2/5

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

  Schema has no property descriptions; description only maps 'command' and hints at eventLimit via 'bounded event collection', but leaves waitMs and command structure/format unexplained, so it does not compensate for 0% schema description coverage.

  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 uses verb 'Send' and specifies resource 'Home Assistant command', plus 'one' to scope. It distinguishes from siblings ha_status and ha_rest by WebSocket bridge and 'socket always closes'.

  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 states 'Send one Home Assistant command' and 'no monitoring or retries', giving negative guidance; 'optional bounded event collection stays within this call' indicates a finite event-collection use. It does not explicitly name ha_status/ha_rest, but the WebSocket/command framing conveys when to choose this over status/REST.

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