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

With no annotations, the description carries the full burden and does meaningfully address it: 'never verified execution' clarifies the check is not an execution proof, and 'No writes or reputation' discloses side-effect safety. It omits return format and any rate-limit/auth details, but the key behavioral caveats are stated rather than left to inference.

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?

Dense and front-loaded: the replay action leads, then parameter behavior, then comparison semantics and safety constraints. Every clause carries information, though the telegraphic fragments ('No writes or reputation.') trade readability for brevity.

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 annotations and no output schema, the description still describes what the comparison reports ('stored/supplied source, canonical equality and pass/fail change'), which partially substitutes for a return-value spec. Combined with the safety notes, it is largely sufficient for an agent to call the tool correctly, with the minor gap being postId semantics.

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 only 33%, so the description must compensate. It adds real meaning for `result` (replaces supplied output, omission replays original) and frames `attachmentHash` as the expected hash. But `postId` and the precise comparison inputs remain undocumented beyond the schema, so compensation is partial.

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 description states a specific verb+resource: 'Replay a public finding against its frozen dataset and expected attachment hash.' This clearly distinguishes it from siblings like get_finding and preview_finding by emphasizing deterministic replay/comparison rather than retrieval or preview, though it never names those siblings explicitly.

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?

It explains the branch condition for the optional parameter ('Optional result replaces supplied output; omission replays original'), which is useful usage guidance. However, it gives no explicit when-to-use-this-vs-alternatives routing against get_finding or preview_finding, so usage is only implied from context.

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