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

Goes well beyond the destructiveHint/idempotentHint annotations by spelling out the exact blast radius: the link dies immediately, in-flight uploads are cancelled, but already-delivered files remain in the material. It also discloses the auth/scope requirement and the zero-cost property.

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-loads the action and its consequence in one sentence, then tacks on the no-op case, permission requirement, and cost as short declarative clauses. Every clause carries distinct information with no restatement of the title.

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 two-parameter, non-read-only mutation with no output schema, it covers consequences, idempotency, permissions, and even the shape of the no-op response field. An agent has everything needed to call it safely and interpret the result.

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?

channel_id is covered by the schema, and the description adds real meaning by clarifying what happens to the entity behind it. The residual gap is project_id, which the schema leaves undocumented and the description only gestures at obliquely with 'the piece's owner'; with 50% coverage this is a modest gap rather than a fatal one.

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 and resource ('Revokes an upload link of a piece') and immediately describes the effect, which clearly separates it from the inverse operation open_channel. It does not explicitly name that sibling as its counterpart, so an agent must infer the pairing from context.

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?

Gives concrete preconditions — 'Only the piece's owner' and 'Requires `write`' — plus the when-not case: revoking an already revoked link is a no-op returning `revoked: false`. What is missing is an explicit pointer to open_channel for link creation or to list_channels for discovery.

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