Server Quality Checklist

Tool Scores

• readA
  4.3/5.0
  Behavior4/5

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

  The readOnlyHint annotation already signals a safe read operation. The description adds valuable behavioral details about error handling ('Errors with a clear message if the topic does not exist') and expiry behavior ('Expired topics are still readable by id'), going beyond what annotations 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 consists of three concise sentences, front-loaded with the primary purpose. Every sentence contributes useful information (purpose, error handling, expiry behavior) without unnecessary verbosity.

  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 simple read operation with one parameter, readOnlyHint, and an output schema, the description covers essential behavioral aspects (error, expiry) and prerequisites. It is complete enough for an agent to decide when and how to call the tool.

  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 100%, so the parameter 'topic_id' is fully documented in the schema. The description adds minimal parameter semantics (only the prerequisite to call discover_topics first), which is a slight enhancement but does not significantly exceed the schema baseline.

  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: 'Read a single topic in full, including its YAML frontmatter.' It specifies both the resource (topic) and the scope (single, full, including frontmatter), and distinguishes it from sibling tools like discover_topics (listing) and write/edit (mutations).

  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 provides contextual guidance: 'call discover_topics first' indicates a prerequisite for obtaining valid topic IDs, and 'Expired topics are still readable by id' clarifies behavior for edge cases. It does not explicitly exclude alternatives, but the guidance is clear.

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

• relatedA
  4.3/5.0
  Behavior4/5

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

  Annotations already include readOnlyHint: true, which conveys the safe read-only nature. The description adds valuable context by specifying the return structure ({id, outbound, inbound}) and the error condition if the topic does not exist. This goes beyond the annotation's basic safety flag and helps set expectations, though it doesn't cover potential edge cases like pagination or depth of linking.

  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 concise, consisting of three sentences: purpose, return format explanation, and error behavior. Every sentence carries useful information without fluff. It is well-structured and front-loaded with the main purpose, making it easy for an agent to quickly grasp and use.

  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 simple tool with one parameter, an output schema, and read-only annotation, the description is complete. It explains what the tool does, what it returns (including semantics of outbound/inbound), and error behavior. The presence of an output schema means return value details don't need to be repeated. No gaps are apparent.

  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 fully documents the only parameter, topic_id, with a description 'Topic id whose link graph to report.' Since schema description coverage is 100%, the description doesn't need to add much. The tool description's mention of 'for a topic' is redundant with the schema. No additional semantic nuance is provided, so baseline 3 is appropriate.

  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: 'Report outbound and inbound wiki-link relationships for a topic.' It uses a specific verb ('report') and identifies the resource ('wiki-link relationships') and scope ('for a topic'). It distinguishes itself from siblings like read (which reads content) and discover_topics (which lists topics) by focusing on link relationships.

  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 provides clear context on when to use the tool (to get link relationships for a topic) but does not explicitly mention alternatives or exclusion criteria. There is enough specificity to infer appropriate usage, but it lacks direct 'use this instead of X' guidance. Given the sibling tools, a brief note on when not to use it would improve it.

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

• deleteA
  4.5/5.0
  Behavior5/5

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

  The description goes well beyond the destructiveHint annotation, explaining that deletion is soft, files are moved to a timestamped trash path, the path is returned for manual restoration, parent folders are pruned when empty, and topics are never unlinked. This provides comprehensive behavioral transparency with no contradictions.

  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 extremely concise, with the main action in the first sentence and supplementary details in two short follow-up sentences. Every sentence adds meaningful information without redundancy.

  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 simple tool with one parameter, an output schema, and a clear annotation, the description covers all essential aspects: the action, the destination, the return value, side effects, and restoration. It is self-contained and leaves no major gaps.

  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 fully describes the single parameter 'topic_id' with 100% coverage and an example. The description adds minor context by showing how the topic_id is used in the trash path template, but this is not essential since the schema already defines the parameter clearly.

  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 identifies the tool as a soft-delete operation for a topic, specifying the destination as a trash path and contrasting with potential permanent deletion. The phrase 'never unlinked' and the return of the trash path distinguish it from related sibling tools like 'sweep' and 'rename'.

  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 this tool: for reversible deletion that can be manually restored. It does not explicitly compare to alternatives like 'sweep' (likely permanent deletion), so it lacks an explicit 'when not to use' statement, but the context of soft-delete and manual restore is strong.

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

• renameA
  4.5/5.0
  Behavior5/5

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

  Beyond the destructiveHint annotation, the description discloses multiple behavioral traits: rewrites wiki links, handles prefix links with an example, refuses if new_id exists, and returns the count of rewritten links. This is rich, actionable 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?

  The description is three sentences, with the core purpose front-loaded. The second sentence adds a concrete example, and the third covers constraints and return value—every sentence earns its place.

  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 covers the operation, edge cases (prefix links, existing new_id), and return value. With an output schema present, there's no need to explain the count format. It's complete for a two-parameter tool.

  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 coverage is 100%, so the schema already documents both parameters. The description adds context about the overall operation but doesn't elaborate on parameter specifics beyond what the schema provides. Baseline 3 is appropriate.

  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 'Move a topic and rewrite wiki links that pointed to it,' giving a specific verb and resource. It also distinguishes the tool from siblings like write, edit, and delete by emphasizing the link-rewriting aspect.

  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 for when to use the tool (moving a topic and updating links) without explicitly naming alternatives. It doesn't provide exclusions or compare to siblings, but the unique behavior of rewriting links implies its specific use case.

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

• sweepA
  4.5/5.0
  Behavior4/5

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

  Annotations only provide destructiveHint=true. The description adds valuable context: the operation is a soft-delete that moves topics to .trash, and dry_run=true is safe, while dry_run=false triggers the destructive action. This explains the behavior beyond the annotation.

  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 only two sentences, front-loaded with the core purpose, and every word earns its place. It explains the behavior, the parameter's role, and the intended usage pattern without any 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 the tool's simplicity (one parameter) and the presence of an output schema, the description fully covers the operation, safety considerations, and usage workflow. No additional return type details are needed.

  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 the dry_run parameter with 100% coverage. The description enriches this by explaining the two-step workflow, clarifying that true is a preview and false performs the move. This adds meaningful context beyond the schema's basic 'lists without moving'.

  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+resource combination: 'List or soft-delete topics whose expiry has passed.' This clearly states the tool's function and distinguishes it from sibling tools like 'delete' (hard delete) and 'read' (general 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?

  The description gives explicit usage guidance: first call with dry_run=true to review, then call with dry_run=false to perform the soft-delete. This is a clear when-to-use workflow. It doesn't explicitly mention alternatives like 'delete' for permanent deletion, but the soft-delete designation implies that distinction.

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

• appendA
  4.7/5.0
  Behavior5/5

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

  The description discloses detailed behavioral traits: insertion with exactly one blank line, heading creation behavior, failure on nonexistent topic, timestamp bumping, and retention never shortening. This goes well beyond the annotation (destructiveHint: true) and gives the agent a clear model of side effects.

  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 compact and front-loaded with the primary purpose. Each subsequent sentence adds meaningful behavior detail without unnecessary fluff. It is well-structured 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?

  Given the tool's moderate complexity, the description covers failure conditions, side effects (timestamp), and retention semantics. Since an output schema exists, return values are not needed in the description. It is sufficiently complete for effective 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 provides descriptions for all parameters (100% coverage). The tool description adds extra meaning for 'heading' (appends under existing ## heading or creates it) and 'retention' (extends but never shortens). This enriches understanding beyond the schema, warranting a score above the baseline.

  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: 'Append text to an existing topic.' The phrase 'without rewriting the whole body' differentiates it from sibling tools like write and edit, making the purpose specific and 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 implies when to use this tool (when adding text to an existing topic without rewriting the whole body) and provides context about behavior (e.g., heading handling, failure if topic doesn't exist). However, it does not explicitly name alternatives or state when-not-to-use, so it falls short of a 5.

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

• discover_topicsA
  4.9/5.0
  Behavior5/5

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

  Beyond the readOnlyHint annotation, the description adds rich behavioral detail: the exact JSON fields returned, newest-first ordering, snippet centering on body matches, default hiding of expired topics, the 'expired' marker when revealed, and reporting of truncation/hidden results. This fully discloses behavior without contradicting 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 front-loaded with the primary purpose and usage directive, followed by a compact list of return fields and behavioral notes. Every sentence contributes unique information; there is no padding or repetition of schema 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?

  Given the tool's complexity (4 parameters, list return with fields, filtering, expiration handling), the description covers all essential aspects: what it returns, ordering, query behavior, expiry handling, and truncation reporting. With readOnlyHint annotation and output schema, nothing is left ambiguous.

  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?

  Input schema already covers all four parameters with descriptions (100% coverage), so baseline is 3. The description adds meaning beyond the schema, notably that query affects snippet centering and that include_expired reveals topics marked with 'expired': true. This enriches the agent's understanding of parameter effects.

  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 'List available topics' — a specific verb and resource that distinguishes this discovery tool from siblings like read, write, and related. It also positions itself as the precursor to mutation operations, further clarifying its unique role.

  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 to 'Call this before read/write/edit/delete/append/rename/sweep', giving a clear when-to-use directive. It also explains optional query and include_expired behavior, which helps the agent decide when to pass those parameters.

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

• editA
  4.9/5.0
  Behavior5/5

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

  Beyond the destructiveHint annotation, the description reveals failure modes (topic not existing, old not found, multiple occurrences without replace_all) and the side effect of bumping the 'updated' timestamp. This is rich behavioral context not present in 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 five tightly written sentences with no fluff. The first sentence defines the core purpose, and each subsequent sentence provides essential failure, side-effect, or alternative information. Nothing is redundant.

  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 an output schema is present, there is no need to explain return values. The description covers purpose, exact behavior, failure modes, side effects, and alternative sibling tools, making it fully adequate for a tool of this complexity.

  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?

  Schema description coverage is 100%, so baseline is 3. The description adds value by contextualizing parameters: e.g., it explains that 'old' appearing more than once causes failure if replace_all is false, which connects parameter semantics to runtime behavior. This is beyond what the schema states.

  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 'Exact-string replacement inside an existing topic' with a specific verb and resource, and distinguishes itself from siblings by explicitly directing metadata changes to write. This is unambiguous.

  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?

  It provides explicit when-to-use guidance ('Exact-string replacement') and an explicit alternative for metadata changes ('To change title, tags, or expiry, use write instead'). It also lists failure conditions that effectively say when not to use without replace_all, aiding correct tool selection.

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

• writeA
  4.9/5.0
  Behavior5/5

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

  Goes well beyond the destructiveHint annotation by detailing overwrite behavior, implicit folder creation, the return payload (resolved id and created/replaced), the 1 MB content limit, and exact retention durations. No contradiction with 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?

  Four tight sentences, no filler. The description is front-loaded with the core purpose, then efficiently covers destructive behavior, path creation, size limits, and retention in a logical order.

  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 tool's complexity, the annotations, and the presence of an output schema, the description covers all essential aspects: purpose, destructive behavior, constraints, return values, and retention options. An agent has enough to select and invoke 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?

  Schema coverage is 100%, so the baseline is 3, but the description adds useful meaning: retention options are expanded with concrete durations (e.g., 'session/today means 24 hours'), and content is given a size constraint. Tags and title are self-explanatory and already well-described in the 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?

  Opens with 'Create or replace a topic' – a specific verb and resource. It distinguishes itself from the sibling 'edit' tool ('use edit for targeted changes') and clearly conveys the overwrite behavior.

  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 directs users to 'edit' for targeted changes, which is a clear when-not-to-use alternative. It also gives practical guidance on splitting large content, notes implicit parent folder creation, and clarifies retention semantics.

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