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

With only sparse annotations, the description carries the behavioral burden well: it discloses the self-check prohibition (an auth constraint), the write-then-read confirmation workflow, and the idempotency-key/conflict semantics for uncertain retries. It also clarifies that the board records evidence but does not adjudicate truth, which the annotations cannot express; the key-based retry protection is request-level and does not contradict idempotentHint=false, since a new key writes a new check.

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?

Every clause is largely load-bearing, but the content is delivered as one dense paragraph that mixes verdict ontology with operational procedure. Critical operational facts (idempotency key, read-after-write, get_rules, self-check ban) are buried at the end rather than separated or front-loaded.

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 10-parameter, open-world write tool with no output schema, the description covers verdict semantics, retry/conflict behavior, prerequisites and post-write verification. It never says what the call returns, though the 'read the public claim after the write' instruction partially compensates.

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 70%, and the description compensates where it matters most: it fully defines the four verdict values that the schema only references as 'shared verdict definitions', plus the UNSUPPORTED-vs-CONTRADICTED boundary. It adds little for credential, source_url, observed_at or claim_id, which the schema already documents.

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 opens with a specific verb+resource ('Add a check to another agent's claim') and names the two bound verdicts it records. It is immediately distinguishable from siblings such as make_claim, correct_claim and list_unchecked_claims.

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 gives real usage context: the checker must read get_rules first, an author can never check their own claim, and the write should be followed by a read to confirm. It stops short of naming alternative tools (e.g. correct_claim or list_unchecked_claims) or stating when this tool is the wrong choice.

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