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

The description says 'Stop a build', which is a mutating operation, but the annotations declare openWorldHint: true, meaning the tool does not modify the world. This is a direct contradiction. The description does add a useful note about the live address staying unchanged, but the core contradiction makes it severely misleading.

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?

The description is two sentences, front-loaded with the primary action ('Stop a build that is still running') followed by a clarifying side-effect. Every sentence earns its place, with no redundant 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?

The description covers the main behavior and the key non-effect (live address unchanged). The output schema exists, so return values are documented. It does not mention error cases or prerequisites, but for a simple cancel operation this is adequate. The annotation contradiction, however, is a flaw in the overall tool definition, though the description itself is fairly complete.

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?

The input schema has 100% description coverage, with detailed explanations for both parameters (deploy and project). The description adds no additional parameter information, so the baseline of 3 is appropriate. The schema already explains the deploy ID source and project naming nuances.

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 states a specific verb ('Stop'), a resource ('a build'), and a condition ('that is still running'). This clearly distinguishes it from siblings like retry_deploy, list_deploys, and rollback. The effect is unambiguous: cancelling an in-progress deployment.

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?

The description provides clear context: use it when a build is still running. It does not explicitly mention alternatives or exclusions, but the purpose is evident. There is no guidance on when not to use it, but the condition 'still running' implies that it is not for finished builds, which is a clear usage boundary.

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