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

Annotations already declare readOnly/idempotent/openWorld, so the bar is lower, yet the description adds substantial non-structured context: execution location (Cloudflare Worker, not caller's machine), data flow to api.osv.dev with nothing sent to Apify, no-storage design, one HTTPS call per ID in parallel, <2s typical with 20s per-call timeout. It also discloses partial-failure semantics (per-ID error rows, retryability) that annotations cannot express. No contradiction with any hint.

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?

Strongly front-loaded with labeled sections (WHAT/WHEN/WHEN NOT/COST/RETURNS/BEHAVIOR/PARAMETERS/EXAMPLE) and dense with information. Minor redundancy: 'no token' and the 'designed not to store inputs/results' claim appear in both COST and BEHAVIOR, which slightly dilutes an otherwise tightly packed definition.

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?

For a 3-parameter, partial-failure-prone network tool the description covers everything an agent needs: routing, cost/privacy posture, error taxonomy with retry guidance, pagination mechanics, and a concrete input/output example. An output schema also exists, so return-value detail is a bonus rather than a gap.

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% (baseline 3), but the description goes well beyond the schema: each ID yields exactly one row in input order, unknown IDs produce a non-retryable VULN_NOT_FOUND versus a retryable OSV_FETCH_FAILED, IDs are matched verbatim with no URL/prefix trimming, duplicates are fetched twice, and pagination requires resending the same ids with the returned nextOffset. These are operational semantics the schema cannot convey.

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 'WHAT' line names a specific verb (Fetch) and resource (full OSV records) and enumerates the fields returned (summary, details, aliases, severity vectors, fixed versions, references). It is unambiguously distinguishable from osv_query_packages and osv_audit_dependencies, which the 'WHEN NOT' line names directly.

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?

Explicit two-sided routing: 'WHEN: You have IDs (from osv_query_packages or a report)' and 'WHEN NOT: To find which vulns affect a package version (osv_query_packages) or a whole manifest (osv_audit_dependencies, paid).' Both alternatives are named with the condition that selects them, leaving nothing to inference.

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