redo

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

With no annotations, the description carries the full behavioral burden and mostly fails: it hints at an optimistic-concurrency check (the revision must match) but never says what happens on mismatch, whether the redo is itself reversible, what state is mutated, or what permissions/session state are needed. The one disclosed trait — revision must match — is the only real behavioral value present.

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 a single short sentence with no filler, which is structurally fine, but the brevity is under-specification rather than economy — the one clause present is cryptic ('显式文档') rather than front-loaded with actionable meaning.

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 mutation tool with no annotations, no output schema, and 0% parameter documentation, the description does far too little: it omits error behavior on revision mismatch, the relationship to undo, and the meaning of the required identifiers. An agent could call it, but would be guessing about failure modes and side effects.

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 0% across 4 parameters, so the description must compensate and does not. '修订' loosely maps to expected_revision, but session_id, document_id, and request_id (including whether request_id provides idempotency) are 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?

The verb 'redo' (重做) is specific and pairs implicitly with the sibling 'undo', but the object '显式文档' (explicit document) is an unusual phrasing that leaves it unclear whether the tool redoes an operation, a document state, or an edit session. An agent can guess it re-applies something that was undone, but the resource is not stated crisply enough to distinguish it confidently from apply_operations.

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?

There is no statement of when to use this versus 'undo' or 'apply_operations', which are the obvious alternatives. The clause '要求匹配修订' implies a precondition on expected_revision, but no explicit when/when-not guidance or exclusion is given.

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