Library Documentation (Context)

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

Annotations already declare readOnlyHint and idempotentHint, so the safe profile is known. The description adds valuable context: fetches from GitHub + npm registry, offers readme/changelog/migration sections, and notes changelog covers 'last 5 versions'. It does not disclose rate limits or error behavior, but with annotation coverage, this is acceptable and adds source and data freshness context.

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

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

The description is moderately sized but well-structured with a front-loaded main sentence, bold section headers, and a clear examples list. Each sentence serves a purpose, though it could be slightly tightened without losing value. The use of bullet points and examples aids scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

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

With no output schema, the description does a good job explaining the tool's capabilities and available sections, but it does not explicitly describe the return format (e.g., markdown text). Given the tool's read-only, informational nature and the inclusion of examples, the description is mostly complete, though a note about output format would make it more complete.

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

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

Schema coverage is 100% with each parameter having a description. The description goes beyond schema by explaining what each section returns (e.g., 'readme: Latest README with API docs...') and provides concrete examples of query usage ('query="runes" for Svelte 5 migration docs'), thus adding meaningful semantic value beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Fetch up-to-date documentation, changelogs, and migration guides for any npm package directly from source', which is a specific verb+resource with clear scope. It distinguishes itself from sibling tools like depsonar_changelog and depsonar_migrate by covering all three sections and adding 'directly from source' as a unique source attribute.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit usage context with 'Use this BEFORE writing code that depends on a library, to get the latest API docs and avoid hallucinating outdated APIs.' It also explains how to combine query and sections with examples, but does not explicitly name alternatives or when-not-to-use scenarios, which would push it to a 5.

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