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

With no annotations, the description carries the burden and does so well: it declares that proposal_weight is untrusted metadata that never ranks, that returned ids are 'born quarantined', that the hash is sealed as a durable anchor, and that hashing-before-checking prevents later selective disclosure. It does not cover auth requirements, idempotency, or size limits (the schema's 64-item cap), leaving some behavioral gaps.

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-loads the critical fact (commit complete set before evaluation) in the first clause and packs several constraints into two dense sentences. The closing rationale about selective disclosure is slightly rhetorical but does justify the ordering constraint, so it earns most of its space.

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, yet the description explicitly enumerates what comes back (candidate_set_id, membership commitment hash/anchor, per-candidate ids) and their quarantine status. Combined with the untrusted-weight semantics, an agent has enough to call this mutation tool correctly without further docs.

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 100%, so query/prompt/generator/candidates/generation_method are all documented in the schema. The description's claims about proposal_weight being untrusted and never confidence largely restate the schema text, so it adds little beyond the structured field it duplicates.

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 ('commit a COMPLETE raw candidate set') and positions it precisely as 'step 1' of a pipeline run 'BEFORE any evaluation'. An agent can distinguish it from siblings like candidate_get and candidate_narrow purely from this framing.

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?

Clearly establishes when to call it: after generation, before any evaluation, and it signals that verification belongs elsewhere ('Nothing is verified here'). It lacks an explicit naming of the alternative tools (candidate_get / candidate_narrow) that follow, so routing is by inference rather than spelled out.

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