执行已注册能力

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

Annotations already mark the operation as destructive and open-world, and the description adds meaningful behavioral caveats: it will not execute arbitrary eval, it executes according to a capability-defined schema, and callers must use the returned assetLocation.url rather than assuming an assets root. No contradiction with annotations is present.

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 compact and each sentence adds a specific operational rule or caveat, with no filler. It is not front-loaded around the core purpose, but it remains tight and useful for a dangerous generic executor.

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 important preconditions, modification guidance, and the no-eval guarantee, but it omits the response shape, error behavior, and does not explicitly instruct the agent to call cocos_capability_describe to obtain the capability schema. Given the tool's open-world and destructive nature, more completion would be justified.

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 0%, so the description must carry parameter meaning, but it only explains expectedRevision and operationId. projectId, capabilityId, instanceId, runtimeInstanceId, and the params object are left unexplained beyond their names; pointing to the capability's schema helps for the params object but not for the top-level metadata.

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 title and description together convey that this tool executes a registered capability, and the description adds specificity by saying execution follows the capability's schema and that the executor will not run arbitrary eval. It is clear enough but does not explicitly contrast itself with sibling execution tools like workflow_execute or build_start.

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 concrete operational context: it mandates calling asset.location before creating resources, points to asset.organize.plan/apply for reorganizing existing assets, and recommends expectedRevision and a stable operationId for modifications. It does not explicitly say when to prefer this tool over sibling execution tools, but the prerequisites and workflow guidance are clear.

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