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

Annotations already establish read-only safety, yet the description adds substantive behavior beyond them: judgments from the calling run are never returned (self-evidence exclusion), obsolete-sweep-resolved findings are filtered by default, and the githubCommentId join is only exact for inline-delivered findings and null otherwise. These are non-obvious filtering and data-integrity traits an agent could not infer from any structured field.

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?

Front-loaded with the core action and each subsequent sentence carries distinct information (return shape, history flag, self-exclusion, obsolete filter). The closing 'Read-only — records nothing' marginally duplicates readOnlyHint=true, a small redundancy rather than a flaw.

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 takes on return-value explanation and does so thoroughly: id, githubCommentId with caveats, full claim, lifecycle, latest verdict and verification. Combined with the explicit filtering rules, an agent has everything needed to call it correctly and interpret results.

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?

At 60% schema coverage, both optional booleans (include_history, include_obsolete) already carry their own detailed schema descriptions, and the description largely restates them rather than adding new semantics. The one genuine addition — 'any lifecycle status' clarifying the returned set — is about scope, not parameter meaning.

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 — 'Read all recorded findings for a PR' — and pins the scope explicitly with '(any lifecycle status)'. An agent can distinguish this from record_finding_verdict or list_tasks without opening the schema, and it names the downstream purpose (recording verdicts by exact id).

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 context is clear: call this to obtain finding ids before recording verdicts, and set include_history/include_obsolete under stated conditions. It does not explicitly name a competing sibling tool or declare when not to call it, so it stops short of the explicit alternatives routing a 5 requires.

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