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

Annotations only flag destructiveHint=true; the description goes well beyond that by disclosing optimistic-concurrency behavior (fails naming the current version rather than overwriting a concurrent write), the non-lossy recovery guarantee (the overwritten state is kept as a new revision), and a hard refusal condition for html documents. This is exactly the kind of behavioral context annotations cannot carry.

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-loaded with the core action, then preconditions, then the refusal warning — a sensible priority order. It is dense and slightly repetitive in restating the expectedVersion contract, but nearly every clause carries distinct information.

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, concurrency-sensitive mutation with no output schema, the description covers the mutation scope, the concurrency contract, the recoverability of the overwritten state, and the one case where the tool must not be used. Nothing an agent needs to invoke it safely 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 description coverage is 100%, so documentId, revisionId, expectedVersion and expectedProjectId are already documented in the schema. The description reinforces expectedVersion's concurrency semantics and revisionId's replace semantics, but adds little that the schema does not already say, so the baseline of 3 applies.

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 names a precise verb and resource ("Restores the document to the state of a past revision") and immediately scopes what is replaced: title, content and language. It also differentiates from siblings by equating the effect to update_document and referencing get_document/list_document_revisions as the source of its inputs.

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?

It states the precondition explicitly (expectedVersion is the version read via get_document before this call), the failure mode if that precondition is violated, and an exclusion with a named alternative: REFUSED on a kind: "html" document, where update_document should be used instead. When-to-use, when-not-to-use and the alternative are all present.

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