Server Quality Checklist

Tool Scores

• resolve_importsA
  4.1/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses one behavioral trait (subpath normalization) and implies a read-only operation. However, it does not explain the return format, how missing packages are handled, or any side effects, leaving some ambiguity for a tool that returns data.

  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, front-loaded with the core action and purpose, and every sentence contributes meaning (what it does, when to use it, how to pass inputs). It is concise without being under-specified.

  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?

  Given the tool's simplicity and full schema coverage, the description explains the 'what' and 'when' well. However, without an output schema, it omits the return structure (e.g., a map of package names to versions) and error cases, making it not fully complete for an agent to anticipate the result.

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

  Parameters4/5

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

  The schema already covers 100% of parameters, so baseline is 3. The description adds value by instructing users to 'Pass bare import specifiers' and clarifying that subpaths are normalized, which is not fully captured in the schema's brief example. This exceeds 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 states a specific verb ('resolve'/'return the exact installed version') targeting a clear resource (a set of imports) and scope ('in this project'). It also distinguishes itself from likely siblings by emphasizing batch resolution ('each') and subpath normalization, making it clear this is for multiple imports.

  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 tells when to use the tool: 'Use this at the start of writing/editing a file' to ground library calls. It clearly indicates the intended context, though it does not explicitly mention alternatives or exclusions relative to sibling tools like installed_version or project_versions.

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

• installed_versionA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries full transparency burden. It discloses data sources (node_modules or lockfile), optional network behavior ('if online, how far behind npm's latest'), and configuration via env var. It doesn't mention failure modes or exact return format but provides meaningful behavioral context.

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

  Conciseness5/5

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

  The description is well-structured: it opens with the core purpose, follows with a usage rationale, then practical configuration. Each sentence adds value and there is no fluff or repetition of schema details.

  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?

  Given no output schema, the description compensates by explaining what info is reported (exact version, range, drift) and how to set the project. It doesn't specify the return format explicitly, but the core information for correct usage is present. It is complete enough for an agent to invoke correctly.

  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 baseline is 3. The description reinforces the projectDir default and env var but does not add new parameter semantics beyond the schema. It does clarify checkLatest's network call, which is a slight enhancement, but not enough to raise the score.

  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: 'Report the EXACT version of a dependency that is installed in the current project right now' and details the source (node_modules/lockfile) plus additional info (range, drift). This clearly distinguishes it from sibling tools like project_versions by focusing on the installed version versus declared or available ones.

  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 strong contextual guidance: 'Reach for this BEFORE writing code against a library' and explains why (model training blends versions). It implies this is the go-to tool for installed-version queries but does not explicitly name alternatives or exclusions, 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.

• project_versionsA
  4.2/5.0
  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 the data source (lockfile), filtering behavior, and that it includes transitive deps by default. It is clearly a read-only list operation, though it does not mention return format or limit semantics.

  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 concise sentences: the first states the action and scope, the second gives use cases. No redundant wording, and the key information is front-loaded.

  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 output schema, the description covers purpose, source, filtering, and transitive deps. Minor gaps remain around explicit return format and limit behavior, but the tool's simple list nature makes these less critical.

  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 baseline is 3. The description adds semantic context for filter ('substring') and directOnly ('whole tree including transitive deps'), but does not elaborate beyond the schema for limit or projectDir, which are already well-documented.

  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 every dependency's installed version in this project (from the lockfile)', giving a specific verb, resource, and scope. It distinguishes itself from sibling tools by emphasizing the whole tree including transitive deps and substring filtering.

  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 explicit use cases: 'Use to audit what's actually present, or to answer what version of X is in here'. This gives clear context, though it does not explicitly name when-not to use or mention alternative sibling tools.

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