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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds real behavioral value beyond them: a journal entry recording who/when/from-what/to-what/why, idempotency on repeat, refusal of 'lean' without audit, and permission scoping. It does not explain that the destructive hint refers to overwriting the previous status value or whether history is retrievable, so not a 5.

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 but front-loaded: the status vocabulary and the naming scheme come first, then conditions, then authority. Some clauses (the journal/consistency sentence) are editorially rich, though each carries usable semantics.

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 5-param mutation with no output schema, the description covers the status domain, identity scheme, the one gating rule, idempotency, side effects (journal, downstream paper/site), and permissions. Only minor gaps remain: no explicit error behavior on invalid status or missing claim, and no note on whether a reason is required for certain transitions.

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 schema already carries parameter meaning (id vs project+label pairing, reason max 1000 chars, statuses from list_claims). The description reinforces the id-or-project+label alternative and gives examples of what 'reason' should contain, but adds little beyond the schema. Baseline 3.

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 (move a claim's status) and enumerates the exact allowed statuses per scale ('math' vs 'law'), which distinguishes it from sibling setters like set_claim_scale or set_claim. An agent can tell precisely what this does without opening the schema.

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 says 'this is the one place a status changes', names the precondition for the 'lean' status (basis bound to code, clean axiom audit, report_lean_audit), states idempotency ('the same status again changes nothing'), and names the authorization requirement (project members who may write). Strong when/eligibility guidance.

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