Server Quality Checklist

Tool Scores

• append_fleetingB
  3.1/5.0
  Behavior2/5

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

  The description reveals the timestamping and file location, but with no annotations, the burden is on the description to disclose mutation behavior (appending is a write), file creation if missing, or formatting details. It doesn't mention reversibility, permissions, or effects on existing content.

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

  Conciseness4/5

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

  Two sentences, no fluff, and the core action is front-loaded. A slight improvement would be specifying whether the block is appended as a markdown bullet or heading.

  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 description is minimal for a tool that mutates a file. It lacks details on file creation, error behavior, or return value, and no annotations exist to fill the gap. The simplicity of the tool mitigates this somewhat, but an agent needs more behavioral 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 coverage is 0%, but the single parameter 'content' is trivially inferable from the description ('append a timestamped block' implies content is the block text). The description gives no additional format or length constraints, but with one obvious parameter, this is adequate.

  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 the tool appends a timestamped block to a dated file in a specific directory, identifying the resource and action. It distinguishes from siblings by implying a low-friction capture path, though it doesn't explicitly name an alternative.

  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 phrase 'Lowest-friction capture' implies this is for quick note-taking, but it doesn't explicitly state when to use it vs. alternatives like create_note or update_note. No exclusions or alternative tool names are given.

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

• search_notesB
  3.3/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of disclosing behavior. It communicates that this is a read-style search operation and that `area` restricts results to 'permanent/guidance' content. It does not clarify match semantics, result ordering, or whether search covers titles, bodies, or metadata, but the core behavior is reasonably clear.

  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 short sentences with no filler. The primary purpose is front-loaded, and the optional parameter behavior is delivered in the second sentence. Every word earns its place.

  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?

  For a simple search tool with an output schema, the description is nearly sufficient: it names the search scope and the optional filter. It is incomplete mainly because the meaning of 'permanent/guidance' is unclear, and there is no guidance about what kinds of area values are valid. Still, the core invocation path is understandable.

  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 both parameters. It partially explains `area` as scoping to 'permanent/guidance' for that area, but this phrasing is ambiguous and unexplained. The required `query` parameter is never explicitly defined, only implied by the phrase 'full-text search.'

  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 action and resource: 'Full-text search across the library.' This is clear and distinguishes the tool from siblings like get_note or list_permanent_notes by its search-focused framing, though it does not explicitly name or contrast those alternatives.

  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 when to use the tool—when you need full-text search over the library—and gives limited guidance on the optional `area` parameter. However, it does not mention alternatives or exclusion conditions, such as preferring get_note for a single known note rather than searching.

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

• list_areasB
  3.4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden of behavioral disclosure. It conveys that the tool exposes six canonical areas and implicitly suggests a read-only retrieval, but it never explicitly states that it returns a list, whether the data is static, or that there are no side effects. This is adequate for a simple zero-parameter tool but not richly transparent.

  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, efficient phrase with no filler. It front-loads the essential information and is appropriately sized for a zero-parameter read-only listing tool.

  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?

  With an output schema present and no parameters, the description largely suffices for a trivial list operation. However, it leaves the action implicit and provides no contextual guidance about when the six areas would matter or how they relate to sibling tools, making it minimally complete rather than fully self-contained.

  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 an empty input schema, so the baseline of 4 applies. No parameter documentation is needed, and the description does not mislead about any arguments.

  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 identifies the resource clearly as 'the six canonical areas of the knowledge library,' which is specific enough to distinguish it from note- and project-related siblings. However, it lacks an explicit verb in the description itself; the action 'list' is only present in the tool name.

  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 guidance on when to use this tool versus alternatives such as list_projects or list_permanent_notes. An agent must infer from the tool name and the word 'areas' when this is appropriate, since the description does not state any context, exclusions, or alternative routing.

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

• get_guidanceA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden, and it does disclose two behaviors: the return format is raw markdown and the selection is 'first matching area'. However, it doesn't explain how 'area' is resolved from a topic-only parameter, what happens on no match, or whether the operation is read-only. The first-matching behavior is valuable, but the area-matching logic remains opaque.

  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 15-word sentence with zero waste. The path template is front-loaded and the matching behavior is appended at the end; every phrase earns its place.

  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?

  For a one-parameter read tool with an output schema, the description covers the core return value and location. Remaining gaps are the undefined 'area' resolution mechanism and no-match error behavior, which are material to predicting the tool's output. It is minimally adequate but leaves clear ambiguities.

  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 0% and the topic parameter has no schema description, so the description must compensate. It does hint that topic maps to a path/file component via the `<topic>.md` template, but it doesn't clarify topic format or matching behavior. The mention of `<area>` in the path is confusing because area is not a parameter.

  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 verb ('Return') and a specific resource (the markdown file at `04-guidance/<area>/<topic>.md`), making the tool's purpose clear. The path pattern distinguishes it from siblings like get_note, though it doesn't explicitly name any alternative. It is not a tautology, and the 'first matching area' phrase adds behavioral specificity.

  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?

  Usage is implied through the resource pattern: this is the tool for fetching guidance-document markdown by topic. However, the description gives no explicit when-to-use guidance, no exclusions, and doesn't mention alternatives such as search_notes or get_note. An agent must infer when this tool is the right choice.

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

• create_noteA
  3.7/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses important behaviors: it refuses to overwrite and returns a relative path. It does not clarify what happens on overwrite refusal (error vs silent no-op) or whether directories are created, but the core safety behavior is explicit.

  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 action and critical overwrite behavior. The kind and area_or_path guidance is formatted clearly, with no filler or redundancy.

  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 4-parameter tool with no annotations, the description covers the key invocation details: valid kinds, area requirement, overwrite behavior, and return value. It doesn't explain how uniqueness/overwrite is determined (path vs title) or error behavior, but the essential usage contract is present.

  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 0%, so the description must compensate. It clearly defines the 'kind' enum values and explains when 'area_or_path' is required versus optional. Title and content are self-explanatory by name, but the description omits any specifics about content format or path syntax.

  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 the tool creates a new note, identifies supported kinds, and notes it refuses to overwrite. This distinguishes it from update (modification) and append (adding to existing), though it does not explicitly name a sibling alternative.

  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 when-to-use guidance or exclusions are provided. The description implies creation use cases via the kind list but does not mention alternatives like append_fleeting for existing fleeting notes or update_note for modifications, leaving the agent to infer routing.

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

• get_noteA
  3.7/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry the behavioral burden. It does disclose that the operation is a read that returns markdown content, which implies no mutation. However, it does not mention behavior when the note is missing or the path is invalid, and 'relative path' is left imprecise.

  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 no filler. It front-loads the action and outcome, making it easy for an agent to parse quickly.

  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?

  This is a simple one-parameter read tool and the output schema exists, so the description does not need to explain return structure. Still, it lacks guidance on error cases and on choosing this tool over search_notes, leaving a small but real gap in situational completeness.

  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 provides almost no semantic help: the only parameter is 'path' with 0% schema description coverage. The description adds that the path is relative, which is useful, but it does not specify relative to what, whether an extension is required, or the expected path format.

  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 ('Return') and a specific resource ('the markdown content of a note'), and identifies the key selection criterion ('by relative path'). This clearly separates it from listing, searching, creating, and updating tools in the sibling list.

  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 intended use is implied: call this when you have a note's relative path and want its markdown content. However, it does not explicitly say when to prefer this over search_notes or list_permanent_notes, nor does it mention that search_notes is the alternative when the path is unknown.

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

• list_permanent_notesA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. 'List all' clearly indicates a read-only, exhaustive listing, but it does not explain how 'within one area' is interpreted (e.g., exact match, hierarchical inclusion), whether results are sorted, or any pagination behavior.

  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 short, front-loaded sentence that directly states the action and scope. Every word contributes meaning, 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.

  Completeness3/5

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

  The tool is simple and has an output schema, so return-value documentation is not required. However, the description is missing useful context about how to obtain a valid 'area' value and how this tool relates to list_areas, leaving an agent to infer that connection from sibling names.

  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 0%, so the description must compensate for the single required 'area' parameter. It partially does by tying 'area' to the scope of the listing, but it does not explain what values area accepts, where they come from (e.g., list_areas), or the expected format.

  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 ('List'), a specific resource ('permanent notes'), and a clear scope ('within one area'). It differentiates from siblings such as list_areas (which lists areas) and search_notes (which searches notes) by emphasizing 'all permanent notes' within a single area.

  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 the use case: when you need all permanent notes in one area. However, it provides no explicit guidance about when to prefer this tool over alternatives like search_notes, nor does it mention when not to use it.

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

• list_projectsA
  3.8/5.0
  Behavior3/5

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

  The word 'List' implies a read-only operation, and the description specifies the exact source directory and inclusion rule, but it does not explicitly state side-effect-free behavior or what happens when no projects match. With no annotations available, the description carries the full burden and provides only minimal behavioral disclosure.

  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 sentence that front-loads the primary action and immediately provides the key filtering detail. Every word contributes meaning, 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.

  Completeness4/5

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

  For a zero-parameter listing tool with an output schema present, the description is largely sufficient: it names the resource, the location, and the inclusion rule. It could additionally clarify whether 'directories under' means immediate children or recursive matches, but overall the context is adequate for this simple tool.

  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 are no parameter semantics to clarify. A baseline of 4 is appropriate because the empty schema leaves no ambiguity and the description correctly focuses entirely on the tool's behavior.

  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 verb 'List' and the resource 'active projects', and further defines what counts as active: directories under `05-projects/` containing a README.md. This specificity distinguishes it from sibling list tools like list_areas, which would target a different hierarchical namespace.

  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 gives the selection criterion but does not explicitly mention when to use this tool versus alternatives such as list_areas or search_notes. There is no when-not guidance, so an agent must infer from the name and description rather than being directed to the right sibling.

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

• save_changesA
  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 clearly reveals the side effects: staging all changes, committing, and pushing to origin/main. It also communicates the approval gate. It does not mention remote/auth failure modes or irreversibility, but the core behavior is transparently stated.

  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: three short sentences that front-load the action and then give the critical usage constraint. Every sentence earns its place, and there is no redundant filler.

  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?

  For a simple one-parameter tool, the description covers the action and the approval condition well. However, the lone optional parameter is undocumented, and with no output schema, the agent is left guessing about return values or default behavior when message is null. These gaps prevent full completeness.

  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?

  There is one optional 'message' parameter with 0% schema coverage, and the description never explains it. An agent can only infer that 'message' is the commit message from the word 'commit'; the description does not state whether it is required, what happens when omitted, or how it is used. With low schema coverage, the description needed to compensate and did not.

  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: 'Stage all changes, commit, push origin main.' This unambiguously identifies the tool as a git save-and-push operation and clearly distinguishes it from sibling tools focused on notes, projects, and pending-change listing.

  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 an explicit condition: 'ONLY call this tool when the user has explicitly approved the change' and provides concrete examples ('save it', 'commit that', 'looks good, push it'). It also states a clear exclusion: drafts iterated without approval should remain uncommitted.

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

• update_noteA
  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 behavioral disclosure burden. It reveals that the operation is destructive ('Overwrite') and that it will refuse to proceed on non-existent paths. This provides important safety and error-behavior context beyond the schema, though it does not detail side effects or permissions.

  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 succinct sentences with no filler. The core action is front-loaded, and the failure condition is stated immediately after, making the behavior easy to parse quickly.

  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?

  The tool has only two required parameters and an output schema, so return values need no explanation. The description covers the primary behavior and a key edge case (non-existent path). Minor gaps remain, such as whether the entire note is replaced or just the content, but 'overwrite' sufficiently implies full replacement.

  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 0%, so the description must compensate. It adds some meaning by clarifying that 'path' must refer to an already-existing note and that 'content' is the new overwriting content. However, it does not describe the path format or any constraints on content, leaving agents to infer from parameter names.

  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 ('Overwrite') and resource ('an existing note'), clearly stating the tool's action. The phrase 'Refuses if path doesn't already exist' differentiates it from create_note and append_fleeting by emphasizing it only modifies existing notes.

  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 indicates when to use the tool: when an existing note must be overwritten. The refusal condition explicitly states when not to use it (when the path does not already exist), though it does not name alternatives like create_note. This is clear usage context without full alternative routing.

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

• list_pending_changesA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the behavioral burden. It discloses that this is a read-only inspection tool backed by git status parsing, which implies no mutation of state. It could explicitly state side-effect-freedom, but the wording strongly signals a safe list 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?

  One sentence, front-loaded with the action and resource, and no filler. The parenthetical adds useful implementation context without bloating the description.

  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 list tool with an output schema available, the description fully covers what the agent needs: what it returns, where the data comes from, and what domain it operates on. Nothing essential is missing.

  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 input schema is empty, so there is nothing for the description to clarify. The baseline for 0-parameter tools is 4, and the description adds no unnecessary parameter noise.

  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 ('Return') and resource ('uncommitted changes in the knowledge-library'), plus a clarifying parenthetical ('parsed git status'). It clearly distinguishes itself from write-oriented siblings like save_changes and from note/project retrieval 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 makes the tool's purpose unmistakable: view uncommitted changes before they are saved or committed. It does not explicitly name alternatives or state 'use this before save_changes', but the context is clear enough that an agent can decide when to invoke it.

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