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

The description adds side effects beyond annotations: 'leaves accepted desired source editable' and 'keeps the last active app running'. The idempotency statement ('Repeating cancellation returns the same terminal status') reinforces idempotentHint=true but adds detail. No contradictions with annotations.

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?

Two sentences, no filler. The primary purpose and key side effects are front-loaded. Every sentence adds value.

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?

Given the presence of an output schema and simple operation, the description covers the main behavior, idempotency, and side effects. It could detail error conditions or what happens to the build object, but for a cancel operation this is adequate. The description is complete enough for an agent to use it correctly.

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?

Only one parameter (build_id) is present, and the schema description ('Build ID returned by create_app or update_app') already provides full coverage. The description does not add further semantic nuance about the parameter, but with 100% schema coverage, 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 clearly states the verb 'cancel' and the resource 'accepted app build', and adds the condition 'before it publishes'. This distinguishes it from delete_app (which removes the app) and get_app_build (which retrieves). The scope is precise and actionable.

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 explicitly states when to use it ('accepted app build before it publishes') and implies that once published or not accepted, this tool is inappropriate. It does not name alternatives, but the context is strong enough to route an agent. Could improve by explicitly saying when not to use (e.g., for deleting the app).

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