Server Quality Checklist

Tool Scores

• connection_statusB
  3.4/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of disclosing behavior. 'Whether... is currently connected' implies a read-only status check with no side effects, but it does not explicitly say the return format (e.g., boolean) or confirm no mutation. This is adequate for a simple status probe but leaves room for ambiguity.

  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?

  A single, well-formed sentence that directly states the essence of the tool. No fluff or redundant inormation. It is front-loaded with the subject 'Angel overlay' and the key state 'connected'.

  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?

  Because there is no output schema, the description should clarify what the agent will receive. 'Whether...' suggests a boolean but is not explicit. The tool is simple enough that this may be sufficient, but the lack of usage context and return-type clarification leaves minor gaps.

  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, so there is nothing for the description to explain. The schema coverage is trivially 100%, and the baseline for 0-param tools is 4. No additional parameter information is needed.

  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 specific resource ('Angel overlay') and the property being checked ('currently connected to this server'). It clearly differentiates from the sibling tools, which are about features. However, it lacks an explicit action verb like 'Check' or 'Returns', so it reads as a state declaration rather than a command.

  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 is provided on when to use this tool versus alternatives. There is no mention of sibling tools or conditions under which connection status would be relevant. The description only states what it reports, not why or when to call it.

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

• get_featureA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description must carry the behavioral burden. 'Read' clearly signals a non-mutating operation, and 'current value' indicates it returns runtime state rather than static configuration. It does not mention error behavior for invalid names, but for a simple read tool this is not a significant gap.

  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 one well-structured sentence with no filler. The core action and object come first, and the source of the parameter is appended efficiently. Every word earns its place.

  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 single-parameter read tool, the description is nearly complete: it specifies the operation, the target, and the prerequisite source of names. The only missing detail is behavior for an unknown or invalid name, but that is not essential for tool 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?

  The input schema already documents 'name' as a control name with an example, and coverage is 100%. The description adds a small useful nuance by saying the name comes from list_features, but otherwise relies on the schema, which is appropriate at this simplicity level.

  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 a specific verb ('Read'), a specific resource ('one menu control's current value'), and the lookup key ('by its name'). The singular 'one' clearly distinguishes this from list_features, and 'Read' distinguishes it from set_feature, so the agent can select it correctly without inspecting schemas.

  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 phrase '(from list_features)' gives explicit context that valid names come from list_features, effectively telling the agent to call list_features first. It does not explicitly exclude set_feature or connection_status, but the single-item read intent is clear enough for this small sibling set.

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

• list_featuresA
  4.2/5.0
  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 warns that danger:true controls can write game memory and require armed writes, which is important side-effect and prerequisite information. It does not explicitly state that calling list_features itself is read-only, but the 'list' wording implies that, and the caveat is applied to the controls, not the listing operation.

  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 focused sentence with a parenthetical expansion of what counts as a menu control and a targeted safety caveat. It is front-loaded with the action and resource, and every phrase contributes to correct usage.

  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 zero-parameter enumeration tool, the description covers what is returned (all controls with current values) and flags an important safety prerequisite for a subset of controls. There is no output schema, so a fully specified return format would be nice, but the description is sufficiently complete for an agent to call this 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?

  The input schema is empty, so the no-parameter baseline applies. The description adds useful output semantics by noting that each listed control is returned 'with its current value,' which goes beyond the empty schema even though there are no parameters to document.

  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, 'List every menu control,' and identifies the resource (overlay menu controls) and scope (feature checkboxes, sliders, comboboxes). This clearly distinguishes it from siblings like get_feature and set_feature, which appear to target single features rather than enumerate all of them.

  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's 'list every' phrasing implies this is the enumeration tool, while get_feature and set_feature likely handle individual lookups and mutations. However, it does not explicitly state when to choose this tool over those alternatives or when not to use it, leaving the usage decision partly to inference.

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

• set_featureA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden of disclosing behavior. It clearly signals a mutating action, warns that danger controls fail unless writes are armed in the overlay, and states the return value is read back after application. This is rich and useful 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.

  Conciseness5/5

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

  Three compact sentences carry all essential information: what the tool does, how to format values, and what to expect from the response. The purpose is front-loaded, and there is no redundant 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?

  For a two-parameter setter with no output schema or annotations, the description is complete: it covers intended input semantics, a key safety caveat, and the return behavior. An agent has enough context to invoke the tool correctly in a supported flow.

  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 covers the parameter basics, but the description adds meaning beyond it: it explains that the combobox value is an option index from list_features and reinforces the boolean/integer expectations. This extra linkage helps an agent select and construct the value correctly.

  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: 'Set one menu control.' It clarifies scope and stands apart from siblings such as list_features and get_feature by clearly addressing a write operation. The examples of control types further disambiguate it from the read-oriented sibling tools.

  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 concrete when-to-use guidance by mapping value types to control kinds and pointing to list_features for combobox option indices. It doesn't explicitly say when not to use this tool versus get_feature, but the context and caveat about armed writes make the usage boundary sufficiently clear.

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