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

Annotations only say readOnly=false, destructive=false, idempotent=true, openWorld=false; the description goes far beyond by disclosing the credential requirement and why it must be repeated, the author-excluded quorum counting rule, the 409 quorum_not_on_single_version payload contents, the doc_hash_mismatch case, and the post-freeze refusals (409 doc_frozen) plus the room's ride-along to state=frozen. This is exactly the mutation/irreversibility context the annotations cannot carry, and nothing contradicts them (idempotent=true and destructive=false remain consistent with a re-freeze and a lock-without-deletion).

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?

It is front-loaded with the secret-handling instruction rather than the tool's action, and the second sentence is a single sprawling run-on threading parentheticals through version_counts, registered_version_counts, counted_on_target, and excluded_author_approves. Every fact is relevant, but the error-payload minutiae read like reference docs and cost scanability.

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 four-parameter mutating state-machine tool with no output schema, the description covers everything an agent needs: credential and role, quorum rule, the exact failure modes with codes, the conflict-detail fields, and the terminal room state that gates room_done. Nothing material is missing.

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% and the schema already documents all four parameters including the Authorization: Bearer alternative and the 'must be latest' constraint. The description adds only marginal meaning beyond it — chiefly that a content_hash mismatch yields a 409 doc_hash_mismatch and that the frozen ref binds 'the exact bytes signed'. Baseline 3 applies when the schema does the heavy lifting.

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 opening clause states a specific verb and resource — 'Freeze version+hash as the doc's immutable accepted ref' — and frames it as 'the docs v-next review→frozen transition', which separates it from the sibling review/commit/accept tools. An agent can tell what state change this performs 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?

Preconditions are spelled out concretely: caller must be the room's LEAD or creator, the lead must have accepted that version, and the D2 quorum must land on ONE version. It also explains the downstream consequence (room_done then lands done). It never explicitly names a sibling alternative to use when these preconditions fail (e.g. room_doc_accept), so the routing is implied rather than stated.

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