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

Annotations already declare readOnly/idempotent/closed-world, and the description layers on genuinely new behavior: no package-specific fixedVersions inferred, pages are fresh lookups rather than snapshots, how to restart after a changed/stale node, the distinction between transmission overflow and upstream truncated, and the warning not to feed the output page object back as input.

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?

Purpose and the full-hash constraint are front-loaded in the first two sentences, and the remaining sentences are all load-bearing pagination/error rules. It is dense and somewhat repetitive of the inline page-field descriptions, which keeps it from a 5.

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 an output schema present, return shape need not be described, and the description instead covers the hard part: multi-step pagination, deferred paths, staleness recovery, and overflow vs truncation semantics. An agent has everything needed to drive this tool correctly.

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%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains the loop pattern (path + offset: page.nextOffset + revision: page.revision), that deferred children start at offset zero without a revision, and that the page object is not valid input. The only gap is that it largely mirrors the page field descriptions rather than introducing new syntax.

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?

States a specific verb and resource ('Query known vulnerabilities for one full Git commit hash') and constrains the input precisely (40-char SHA-1 or 64-char SHA-256, case-insensitive, abbreviated rejected). It also routes to the sibling osv_get_vulnerability for full records, distinguishing this from that tool.

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?

Explicitly names an alternative ('use osv_get_vulnerability for full records') and gives detailed when/how rules for pagination (repeat original input with overflow.page, follow nextOffset/revision). It does not, however, contrast with osv_query_package or osv_query_batch, so the choosing-by-input-shape guidance is left partly implicit.

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