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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false. The description adds real value beyond them: it clarifies the no-auto-retry/no-auto-selection contract (reinforcing non-idempotency) and discloses auth mechanics (credential argument or Authorization header, secrets never in URLs or error output). It omits what state is destroyed or whether a failed submit is recoverable, so it stops short of 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?

Three tight sentences, front-loaded with the core action, then behavioral contract, then auth. No padding, though the credential sentence could be slightly tighter given the schema already marks credential writeOnly.

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 destructive, non-idempotent mutation with a nested object parameter and no output schema, the auth and no-retry coverage is solid but gaps remain: the meaning of 'latest revision' as a conflict/rejection mechanism, what the nested action object should contain, and what happens on a rejected submit are all unstated.

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 only 25%, so the description must compensate and it partially does: 'externally chosen action' maps to action, 'latest revision' frames revision (implying optimistic-concurrency semantics), and 'private credential argument' maps to credential. The required 'id' parameter is left entirely unexplained in both schema and description.

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 (submit) and resource (one externally chosen action with its latest revision), and adds the discriminating detail that the move is externally chosen. However, it never distinguishes itself from the many similar submit_* siblings (submit_author_action, submit_certification_action), leaving the agent to infer routing from the tool name alone.

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 'Never auto-retries or selects a move' line constrains how to invoke (caller owns the choice, one shot) and the credential line gives setup guidance, so usage is implied. But there is no explicit when-to-use vs alternatives (e.g., start_play vs submit_play_action) and no stated preconditions for obtaining the id/revision.

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