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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the description's job is to add behavioral nuance. It does: the identity/security model (no key is ever requested, private key never leaves the user, hostile pages), the utterance ceilings (400 BAD_UTTERANCE above maxLimit, silent capping within limit), the commentary publicity ('public after the move applies'), and the signature construction. This goes well beyond the schema and annotations, though it doesn't describe response/error behavior beyond the 400 case.

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?

The description is dense but front-loaded: the first sentence states the action and payload, and the security paragraph is a single coherent block. Every sentence adds information; there is no filler. It is longer than ideal, but the length is justified by the security model and utterance rules that are not available elsewhere. The structure could be slightly improved by separating the security note from the move semantics, but it is not disorganized.

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 signed mutation tool with no output schema, the description covers the essential call semantics: payload shape, move notation, embedded resign/draw_offer, utterance constraints, commentary visibility, and the authentication model. It does not describe the success response shape or error cases beyond BAD_UTTERANCE, but the absence of an output schema and the presence of rich parameter descriptions make this a reasonably complete picture. An agent can invoke this correctly without guessing.

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 the baseline is 3. The description adds meaning beyond the schema by explaining the move field's two forms (notation string or { index } into legal_moves), the utterance behavior ceilings, the commentary publicity, and the signature scheme. It also clarifies that game_id must equal the path id and that body.signature is part of the signed body. This is meaningful added value, though some of it overlaps with the schema's own descriptions.

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 precise verb ('Submit a signed move') and names the exact payload shape ({ game_id, turn_index, move: notation | { index }, commentary?, utterance?, resign?, draw_offer?, signature }). It clearly distinguishes this from siblings like legal_moves, offer_draw, and resign by framing it as the single action that submits a move with optional embedded resign/draw_offer/commentary/utterance. The parenthetical '(signed)' and the identity paragraph reinforce what kind of action this is.

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?

The description gives strong context for when to use the tool: it is the move-submission endpoint, and it explicitly says resign and draw_offer are embedded options, which routes an agent away from separate siblings like resign and offer_draw. It also explains when utterance is allowed (speech games only) and when it is rejected (games without a speech channel). It does not explicitly name sibling alternatives like 'use resign instead when...' but the embedded-option wording and speech-channel conditions provide clear usage boundaries.

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