finding_details

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, yet the description still adds real behavioral facts: metadata/traffic are null when unknown, the evidence page is bounded but does not change the exact affected count, and the source is an immutable row index. That null-semantics and count-invariance detail goes beyond the annotations, though return shape and failure modes are unaddressed.

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?

Three short sentences, front-loaded with the core action and then the two non-obvious behavioral caveats. No filler; the only mild cost is jargon like 'immutable row index' that an agent may not map to anything concrete.

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?

No output schema exists, and the description does hint at return contents (finding plus evidence page, nullable fields), which partly compensates. It still omits page-sizing guidance and any notion of what happens when auditId/findingId don't match, leaving the picture adequate but incomplete for a 4-parameter lookup tool.

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 description coverage is 0% across 4 parameters, so the description carries the full burden — and it only alludes to paging via 'bounded page'. It never explains limit/offset defaults or bounds (20 default, 100 max), nor what auditId + findingId jointly identify. With a limit/offset pair present, pagination semantics are a notable omission.

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 ('Return'), a precisely scoped resource ('one computed finding and a bounded page of affected URL evidence'), and the singular 'one' implicitly distinguishes it from list_findings. It never names the sibling tool or the id-based lookup condition, so full sibling differentiation is left to inference.

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?

Usage is implied rather than stated: fetching 'one' finding presupposes a findingId obtained from list_findings, and 'bounded page' hints at limit/offset use. There is no explicit when-to-use, when-not-to-use, or named alternative, so an agent must infer the workflow.

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