Server Quality Checklist

Tool Scores

• expressA
  3.6/5.0
  Behavior4/5

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

  Annotations only say the operation is not read-only, not idempotent, and not destructive; the description adds that the expression is temporary and that the firmware owns animation, which explains the device-driven temporal behavior. The sequence/message interaction is a useful behavioral disclosure beyond the schema. It does not describe possible side effects or return behavior, but the annotations provide no contradictions and the output schema covers return shape.

  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 sentences, front-loaded with the core purpose, no filler; the conditional note earns its place because it prevents a common invocation error. This is an ideal size for this tool.

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

  Completeness2/5

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

  Despite output schema and annotations, the definition is not complete enough for an agent to correctly use a complex 11-parameter tool. The most important required field (affect) and several behavior-shaping parameters are unexplained, and there is no mention of when temporary expressions expire or how firmware-sequenced expressions interact with other calls. The sequence/message note helps but is the only operational guidance.

  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?

  With 0% schema description coverage and 11 parameters, the description must carry the burden and largely fails to. It only explains the message/sequence relationship; the required affect parameter and key controls such as priority, gaze, intensity, ttl_ms, autonomy, text_mode, and behavior_mode are left undefined.

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

  Purpose4/5

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

  The phrase 'Show one temporary semantic expression on the local face' names a specific verb, resource, and scope, and 'temporary' distinguishes it from persistent state changes. It does not explicitly contrast with sibling tools like neutral or face_status, so it misses the top bar for sibling differentiation.

  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 direct conditional guidance: when sequence is set, omit message so the device can perform its coordinated eye/OLED beat. It conveys this is the tool for showing a temporary expression, but it never mentions when to prefer neutral, face_status, or face_capabilities instead, so exclusions are absent.

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

• face_statusA
  3.6/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds value by disclosing which specific status fields are read, though it does not discuss connection semantics or potential error conditions. No contradiction with annotations exists.

  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 a single, front-loaded sentence that efficiently lists exactly what the tool reads. Every word earns its place, and there is no redundant or filler content.

  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?

  For a zero-parameter, read-only status tool with an output schema and rich annotations, the description is complete. It covers the key status areas an agent would need to decide whether to call this tool, and no additional behavioral context is necessary.

  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 zero parameters and the schema is empty, so there is nothing for the description to explain. A baseline of 4 is appropriate for zero-parameter tools because no parameter ambiguity exists.

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

  Purpose4/5

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

  The description states a clear verb ('Read') and a specific resource ('YouAndEye status'), and enumerates the exact status dimensions: connection, active expression, eye renderer, mouth mode, frame timing, and misses. It does not explicitly contrast with siblings like express, face_capabilities, or neutral, but the read-versus-action distinction is evident from the wording.

  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 is given about when to use this tool versus the sibling tools. The read-only framing implies it is appropriate for checking state rather than changing it, but the description does not state exclusions or alternatives.

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

• face_capabilitiesA
  4.3/5.0
  Behavior4/5

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

  The annotations already establish readOnlyHint, idempotentHint, and non-destructive behavior, so the description only needs to add context beyond those. It does so by noting that the tool describes connection state and limits, which is behaviorally relevant to an agent deciding whether local state might be stale or constrained.

  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 a single, front-loaded sentence with no filler. Every listed item adds meaningful detail about what the tool returns, making it efficient and easy to parse.

  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?

  This is a simple, zero-parameter read-only introspection tool. The annotations cover safety, the output schema covers return structure, and the description enumerates the main content areas. Nothing essential is missing for an agent to invoke and interpret the tool correctly.

  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?

  There are zero parameters, so the description does not need to explain argument semantics. The baseline of 4 for zero-parameter tools applies, and no information is missing on this dimension.

  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 ('Describe') with a clear resource ('YouAndEye capabilities') and enumerates the exact content categories: affects, sequences, channels, limits, and local connection state. This sets it apart from sibling tools like express, face_status, and neutral, which are action/status-oriented.

  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 implies this tool is used to discover what the system supports and its connection state, but it does not explicitly say when to choose this over siblings or when not to use it. The context is clear enough for a simple read-only capability query, but there is no explicit guidance on alternatives.

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

• neutralA
  4.5/5.0
  Behavior4/5

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

  The description adds concrete behavioral context beyond the annotations: it clears pending expressions and restores a safe autonomous neutral face immediately. This complements the idempotentHint and clarifies that the operation has a calming/reset effect rather than a persistent destructive one.

  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 a single, concise sentence that front-loads the core action and states the immediate result. Every phrase earns its place, with no filler or redundant restating of the title.

  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?

  For a zero-parameter tool with an output schema and rich annotations, this description is fully sufficient. It explains the operation, the effect, and the safety-oriented outcome, so an agent can invoke it correctly without additional context.

  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 zero parameters and the schema coverage is trivially 100%, so there are no parameter semantics for the description to explain. The baseline of 4 applies because the description accurately describes the tool's action without any parameter ambiguity.

  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 specific verbs ('Clear', 'restore') and a clear resource ('pending expressions', 'safe autonomous neutral face'). It clearly distinguishes this from siblings like express, face_status, and face_capabilities by describing a state-resetting operation.

  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 implies when to use the tool: when there are pending expressions that should be cleared and the face should return to neutral. It does not explicitly name alternatives or exclusions, but the intended context is unmistakable from the action described.

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