Server Quality Checklist

Tool Scores

• restore_textD
  1.3/5.0
  Behavior1/5

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

  With no annotations, the description carries the full burden. It does not disclose any side effects, permissions, or even what 'restoration' entails or what happens to the input data. The mention of 'legacy mode' is opaque without further context.

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

  Conciseness2/5

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

  The description is extremely short, but this is under-specification rather than concise effectiveness. It lacks essential details and does not front-load any actionable information.

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

  Completeness1/5

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

  For a 4-parameter tool with no annotations, no param descriptions, and an opaque behavioral contract, the description is woefully incomplete. It fails to provide even a baseline understanding of what the tool accomplishes.

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

  Parameters1/5

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

  Schema description coverage is 0%, and the description provides no explanation for any of the four parameters (text, mapping, restoration_session, trusted_local_review). The tool name and vague narrative give no clue to their roles.

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

  Purpose2/5

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

  The description mentions 'restore' and 'opaque session' but does not specify what is restored, what qualifies as opaque, or how it differs from sibling tools like 'prepare_for_external_ai' or 'redact_text'. It is not a complete tautology but is far from a clear action-resource statement.

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

  Usage Guidelines1/5

  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. The phrase 'direct mappings require explicit legacy mode' hints at a condition but does not explain when or why to invoke the tool.

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

• analyze_textD
  1.9/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of disclosing behavioral traits, but it only mentions that 'raw details require enabled debug mode.' This discloses a minor behavioral aspect (debug-mode dependency) but says nothing about side effects, read/write behavior, performance, or side effects. It doesn't even clarify whether the tool is purely read-only or if it has any external impact.

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

  Conciseness2/5

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

  The description is a single 10-word sentence, which is concise in length, but it sacrifices essential information. It front-loads the vague phrase 'lower-level local' and buries the only concrete behavior (debug mode) at the end. It is not 'concise' in the sense of packing essential details efficiently; it's merely short and uninformative.

  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 having only 3 parameters and an output schema, the tool description fails to explain what the function does, what it returns, or how it fits in the workflow alongside siblings like prepare_for_external_ai or create_safe_copy. The mention of debug mode is an isolated detail with no context. The description is incomplete for an agent to use this tool effectively, even with the output schema available.

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

  Parameters1/5

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

  Schema description coverage is 0%, so the description absolutely must explain the meaning of 'text', 'policy', and 'response_mode', but it does not. The description provides zero guidance on how parameters interact, what valid values exist (no enums), or how defaults like 'minimal' affect output. The description adds no value beyond what the bare parameter names suggest.

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

  Purpose2/5

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

  The description 'Lower-level local review tool' gives a vague sense that the tool performs low-level local analysis but never specifies what 'review' or 'analyze' actually does, what input it processes, or what kind of output it produces. It does not clearly differentiate itself from sibling tools like redact_text or restore_text beyond a weak 'lower-level local' qualifier. The mention of raw details requiring debug mode hints at verbosity control but not purpose.

  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?

  There is no explicit guidance on when to use this tool versus alternatives. The phrase 'lower-level' implies a contrast with possibly higher-level siblings, but no alternative tool is named and no conditions for selection are given. No context, prerequisites, or examples are provided, making it hard for an agent to decide when this tool is appropriate.

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

• create_safe_copyC
  2.4/5.0
  Behavior1/5

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

  With no annotations, the description must explain side effects, but it only states 'write'. It does not mention that this is a state-changing (potentially destructive) operation, whether it overwrites files, or any security or permissions considerations. The user is left without awareness of implications.

  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 with no unnecessary words. It is efficient and directly states the primary action, earning a perfect score for conciseness.

  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?

  The tool lacks essential context: what constitutes 'sanitized content', how the policy parameter affects behavior, and what the return value or success criteria are. Even though an output schema exists (per context), it is not described, and the description alone is insufficient for a user to fully understand the tool's behavior.

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

  Parameters1/5

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

  The description does not elaborate on any of the three parameters (policy, content, filename). Since the schema provides no descriptions, the description should clarify their roles, especially the 'policy' parameter with a default value. It fails to add any meaning beyond the raw names.

  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?

  Clearly states the action (write) and the resource (sanitized content to a configured directory), and implies a specific function distinct from sibling tools like analyze or redact. However, it lacks detail on what 'sanitized' entails and the exact scope of 'only'.

  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?

  Provides no guidance on when to use this tool over the siblings. It does not mention prerequisites, conditions, or scenarios that would call for creating a safe copy. The word 'only' hints at a restriction but does not explain when this should be chosen.

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

• prepare_for_external_aiC
  2.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'prepare text locally' and 'return only approved safe output' but doesn't explain what 'prepare' entails, what 'approved safe' means, or any side effects, permissions, or limitations. The description is too vague to convey meaningful behavioral traits.

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

  Conciseness3/5

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

  The description is a single sentence, which is concise, but it's under-specified. It front-loads the 'Recommended' label but lacks substantive content. While there's no waste, the brevity comes at the cost of clarity, so it's not effective conciseness.

  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?

  Given the tool has 4 parameters, no annotations, and an output schema, the description is incomplete. It doesn't explain the purpose of the parameters, the expected output, or how this tool fits into the workflow. The presence of an output schema helps, but the description still fails to provide essential context for correct invocation.

  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 description coverage is 0%, so the description must compensate for explaining parameters. It doesn't mention any of the four parameters (text, policy, language, response_mode) or their semantics. The description adds no value beyond the schema's basic type definitions, leaving the agent without guidance on how to set these parameters.

  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 the tool prepares text locally and returns only approved safe output, which gives a general sense of purpose. However, it doesn't specify the exact verb+resource relationship or clearly distinguish it from siblings like redact_text or create_safe_copy, which likely have overlapping functions.

  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?

  The description begins with 'Recommended' but provides no explicit guidance on when to use this tool versus alternatives. It doesn't mention when not to use it or name any sibling tools as alternatives, leaving the agent to infer usage context.

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

• redact_textC
  2.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'lower-level compatibility tool,' which hints at its nature but does not state what redaction behavior occurs, how policy or response_mode affect results, or any side effects. This is a significant transparency gap.

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

  Conciseness2/5

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

  The description is a single sentence with no filler, but it is under-specified rather than concisely useful. It omits the tool's core action and parameter semantics, so brevity comes at the cost of essential information.

  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?

  For a tool with 3 parameters and no annotations, this description is far from complete. The output schema may cover return values, but the description fails to explain the tool's behavior, parameter meanings, or when to use it beyond preferring a sibling.

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

  Parameters1/5

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

  Schema description coverage is 0%, and the description mentions no parameters. The schema provides names and defaults but no semantics for policy or response_mode, and the description does nothing to compensate for that lack of meaning.

  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 identifies the tool as a 'lower-level compatibility tool' but never explicitly states that it redacts text; the core action is implied only by the tool name. It does distinguish itself from prepare_for_external_ai by saying 'prefer' that sibling, but the actual function remains vague.

  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 explicitly says 'prefer prepare_for_external_ai,' which provides a clear alternative and a when-not-to-use signal. However, it does not explain when the compatibility path should actually be used or contrast with the other siblings like analyze_text or restore_text.

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