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

No annotations exist, so the description must carry the behavioral burden. It does: clarifies stored crawl output, that it does not reproduce a renderer, does not verify unseen images, and can return unavailable/stale. It doesn't mention mutation/side effects, but 'Read' plus stored data implies a safe lookup.

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?

Four tight sentences cover purpose, required inputs, return values, edge cases, and limitations with no redundant filler. Easy to parse and highly actionable.

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 read-only retrieval tool with no output schema or annotations, the description covers inputs, outputs, staleness, and key limitations. It doesn't detail failure response formats or prerequisites for audit findings, but the essentials are all present.

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 has 0% descriptions, so the description must compensate. It names all five required parameters and tells the caller where they come from ('from audit findings'). It doesn't define each hash or the locator pattern, but the names and schema patterns are identifiable and the provenance guidance is a meaningful addition.

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 precise read operation on a single artifact ('extracted content for one section finding'), names the five identifying inputs, and enumerates the exact return payload. This clearly sets it apart from broader get/list/update siblings.

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 tells the caller to supply the five fields from audit findings and sets expectations for unavailable/stale results. Could name sibling tools for routing, but the provenance instruction is strong enough.

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