Server Quality Checklist

Tool Scores

• list_notesA
  4.3/5.0
  Behavior5/5

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

  In addition to the annotations (read-only, idempotent, non-destructive), the description adds meaningful behavior: ordering of results, preview semantics, an explicit explanation of the substring behavior, and clarity about total_count exceeding returned results when limit truncates the page. This is exactly the kind of behavioral context the description should 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 is three concise paragraphs with a front-loaded summary, a filter guidance section, and a brief output-shape section. Every sentence contributes necessary behavioral or usage detail, and the structure makes it easy for an agent 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?

  The description covers the core operation, ordering, filtering behavior, returned entry fields, total_count semantics, and limit-pagination behavior. Combined with a rich output schema and the read-only annotations, virtually everything an agent needs to invoke this tool correctly and interpret the default behavior is present.

  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 covers both parameters thoroughly: limit defines maximum notes with defaults and bounds, query explains the case-insensitive substring filter and omission. The description restates some of this guidance but does not add significant new meaning for the parameters; its advice about using one distinctive word is minor beyond the schema's coverage.

  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 clearly states a specific action ('List notes') and a distinctive resource, and also specifies the ordering (most-recently-updated first) and output shape (previews), which precisely distinguishes it from the single-record sibling get_note. It doesn't explicitly call out the sibling, but listing versus retrieving a single note is semantically self-evident.

  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 usage guidance for the query filter: it explains that the filter matches case-insensitive substrings, warns that it is not fuzzy or semantic, and counsels preferring one distinctive word over a phrase. It also says to omit the filter to browse everything, but it doesn't explicitly contrast list_notes with get_note for retrieving a single full note.

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

• create_noteA
  4.5/5.0
  Behavior4/5

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

  Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description reveals the result shape (returns note with generated id), a critical error condition (case-insensitive title collision), and a routing fallback. This adds real behavioral context without 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 sentences, the most important return behavior up front, followed by the duplicate-title warning and alternative. Each sentence adds unique operational value; there is no padding.

  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?

  With only two parameters, one required, and a full output schema, the description covers everything an agent needs: what the tool does, what it returns, key constraints, and the correct sibling for modification. Nothing essential is missing.

  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 schema already documents both parameters well. The description adds only the case-insensitive uniqueness nuance beyond the schema's existing 'Must be unique' note. That is small extra value, consistent with the baseline 3 for high 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 uses a specific verb-resource pair ('Create a new note') and clearly states the distinguishing behavior: returning the generated id for later calls. It also contrasts with update_note by pointing out that duplicate titles are errors, making the tool's role unmistakable among its siblings.

  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?

  The description explicitly names when not to use this tool ('if the user wants to change an existing note, use update_note') and clearly flags the uniqueness constraint that should silence spurious create attempts. This gives the agent direct decision support.

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

• get_noteA
  4.5/5.0
  Behavior4/5

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

  Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful context about return behavior (full note body) and explicitly documents a limitation ('does not accept titles'), which goes beyond 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 compact and front-loaded. The first sentence conveys the core purpose, and the second sentence gives the exact context needed to avoid common mistakes without unnecessary elaboration.

  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?

  A single-parameter read operation with annotations, a full output schema, and clear sibling differentiation. The description covers all functional details needed to invoke the tool correctly; nothing important is missing.

  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% and the parameter description already says 'Id of the note, as returned by list_notes.' The tool description reinforces that note_id comes from list_notes or create_note and that titles won't work, but does not add significant meaning beyond 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?

  The description states a specific action: 'Read one note in full by `id`.' It names the resource and the mechanism, and the first sentence identifies the tool as the way to get a note's complete body, distinguishing it from list previews.

  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?

  The description explicitly says to use this tool whenever a note's complete body is needed, notes that list_notes previews are truncated at 120 characters, and clarifies that IDs come from list_notes or create_note and that titles are not accepted. This provides clear when-to-use and when-not-to-use guidance.

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

• update_noteA
  4.5/5.0
  Behavior5/5

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

  Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description clearly discloses the destructive overwrite behavior: it replaces, does not merge, and explains the semantics of omitting or passing null. It also flags the risk of losing current text and instructs the agent on the safe pattern (get_note first). 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?

  The description is compact and front-loaded with the core function. Every sentence serves a distinct purpose: state the operation and return value, warn about overwrite semantics, explain null/omit behavior, and provide the append workflow. No redundancy or filler.

  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 output schema is present, return values are already documented. The description covers the essential behavioral nuance (no merge, omission semantics) and the critical alternative workflow for append. An agent has everything necessary to call the tool correctly without external context.

  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% and the schema already explains that null keeps the current value for both fields. The description adds the clarification that omitting a field also leaves it alone, which is a small extra, but overall it does not materially extend the schema's parameter documentation.

  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?

  States a specific verb (Overwrite), resource (title and/or content of an existing note), and outcome (return the updated note). This clearly distinguishes the tool from its siblings list_notes, get_note, create_note, and delete_note.

  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?

  Provides clear context for use: modifying an existing note by overwriting fields. It also gives explicit guidance for the alternative of appending content, telling the agent to call get_note first and pass the full combined text. However, it does not explicitly state exclusions such as 'use create_note for new notes,' though this is implied by 'existing note.'

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

• delete_noteA
  4.7/5.0
  Behavior5/5

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

  While annotations already set destructiveHint=true, the description adds critical context: the deletion is permanent, content is not recoverable, and it returns what was removed. This warns about irreversibility and the need for confirmation beyond the annotation's binary hint.

  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 two sentences, front-loaded with the core action, and every clause earns its place. The caution and verification guidance are placed logically without waste.

  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 tool is simple (one parameter, no nested objects, has output schema). The description covers what the tool does, the consequence, and the necessary verification pre-step. Nothing an agent needs to call it correctly is missing.

  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 schema covers the only parameter note_id with a clear description 'Id of the note to delete'. Since schema description coverage is 100%, the baseline is 3. The description refers to the parameter as `id` but adds no new format or semantic detail beyond 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?

  The description states a specific verb 'delete' with a specific resource 'note' and the return behavior 'return what was removed'. It distinguishes from siblings like create, get, list, update by naming the destructive action unambiguously.

  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?

  The description gives explicit guidance on when to use this tool: confirm the id with list_notes or get_note before calling when the note was identified by description. This directly addresses potential misuse and surfaces the appropriate alternative behavior.

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