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

Annotations cover readOnly=false/openWorld=true, but the description adds the failure mode for accepted proposals, the externally visible side effect ('the buyer sees the proposal withdrawn'), the default confirmation gating with an opt-out, and the authentication requirement. That is well beyond what the structured fields disclose.

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 action and its scope, then the exception, side effect, and confirmations; every sentence carries information. However, the two confirmation sentences ('you confirm each call' and 'confirm with the user before each call') restate the same requirement, which is slight redundancy.

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 single-parameter cancel with no output schema, the description covers the action, precondition, failure behavior, external visibility, auth, and confirmation policy. The only gap is that the success response is never characterized, though that is minor for this tool class.

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?

One parameter with 100% schema description coverage ('Proposal ID from list_proposals'), which already tells the agent where to obtain the value. The description only implies single-proposal scope ('Cancels one pending proposal') and adds no format or sourcing detail beyond the schema, so baseline 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?

Specific verb+resource with scope qualifiers: 'Cancel a proposal the buyer has not accepted yet. Cancels one pending proposal.' Clearly separates itself from peopleperhour_send_proposal, list_proposals, and create_offer, and the accepted-proposal exclusion further narrows the target.

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 explicit when-to-use ('use it before sending a corrected one'), when-not ('An accepted proposal cannot be cancelled and the call fails'), and operational preconditions (user confirmation each call, Cotlet API key with app access). An agent has everything needed to decide whether to call it.

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