Server Quality Checklist

Tool Scores

• verify_packagesA
  3.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full behavioral disclosure burden. It mentions returning 'a verdict per name' but does not disclose important behaviors like how invalid names are handled, whether verification is concurrent, what the verdict format is, or any rate limits. The description is too vague for a tool with no annotation support.

  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 purpose ('Batch version of verify_package'), then immediately provides usage guidance. Every sentence contributes value without redundancy or fluff.

  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 low complexity (single parameter, no output schema), the description explains purpose and usage but omits return format and edge-case behavior. Without an output schema, the description should at least hint at what 'a verdict per name' looks like (e.g., boolean, object with reasons). It is adequate but has clear 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 schema already provides 100% coverage for the single parameter 'names,' including a descriptive example ('['react','reqeust','@acme/does-not-exist']'). The description adds batch usage context but does not add new parameter-specific meaning beyond what the schema offers, so the baseline of 3 applies.

  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 explicitly states it is a 'Batch version of verify_package' and explains the action: 'pass every dependency you're about to add' and 'get a verdict per name.' This clearly identifies the verb (verify), resource (multiple package names), and distincts itself from the sibling verify_package by emphasizing batch processing.

  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 timing context: 'Use before applying any change that adds dependencies, so a single hallucinated or typosquatted name is caught before install.' It implies usage for batch checks but does not explicitly state when not to use it or mention the single-version alternative beyond the 'Batch version' phrasing. Thus it has clear context but no explicit exclusions.

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

• verify_packageA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries full disclosure burden. It transparently explains the output: 'Returns a verdict (SAFE / CAUTION / SUSPICIOUS / DOES_NOT_EXIST) with the reasons' and lists the criteria (existence, age, downloads, deprecation, edit-distance). It also communicates the safety rationale. It does not mention whether the tool makes network calls or has side effects, but for a verification tool this is not a significant gap.

  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 that flow logically: purpose, when to use, and output/behavior. It is front-loaded with the core function, and every sentence provides meaningful information without fluff. The structure is easy to parse and complete.

  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 the tool's low complexity (one parameter, no output schema), the description is highly complete. It explains the return values and the reasons, which substitutes for an output schema. It also addresses the risk context. However, it could be slightly richer by clarifying how to act on CAUTION or SUSPICIOUS verdicts, but this is not 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?

  The input schema already describes the 'name' parameter with high coverage (100%). The description reinforces its meaning by saying 'the exact npm package name you intend to install' and ties it to the safety check, but it doesn't add new syntactic details beyond the schema. Therefore, a baseline score of 3 is appropriate.

  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's purpose: 'Check that an npm package name is REAL and safe' and mentions it returns a verdict. It is specific about the resource (npm package name) and the action (checking). However, it does not explicitly differentiate from the sibling tool 'verify_packages' (plural), which may handle multiple packages, so it doesn't fully distinguish between them.

  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 explicit when-to-use guidance: 'Reach for this whenever you are about to add a dependency you are not 100% certain exists' and warns against hallucinated package names. It also gives a clear exclusion-like rule: 'If it doesn't exist, do not install it.' However, it does not mention alternatives or explicitly say when not to use this tool (e.g., when verifying multiple packages, use the sibling).

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