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

Annotations cover the safety profile (readOnly=false, openWorld=true, idempotent=false, destructive=false), and the description adds genuinely useful context on top: credential scoping (parent key/token, never the admin key), inherited enforcement of scope/expiry/approvals/ancestor budgets, and a hard depth cap of five. It omits what a successful delegation returns or whether it can be revoked.

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?

Three tight sentences with no filler; the delegation target leads, followed by the credential model and the inherited constraints. Every clause carries 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?

For a non-readonly, open-world mutation tool with eight parameters and no output schema, the description does well on the security/scope model but leaves the core 'actions' payload and the ttl/max_calls limits unexplained. Adequate, but not complete for the tool's complexity.

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 a middling 63%. The description reinforces the meaning of app_key and run_token (parent credentials) but says nothing about the required actions array, label, ttl_seconds or max_calls, leaving the most complex required parameter undocumented in prose.

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+resource ('hand a narrower run to another active app in the same project'), which is meaningfully more precise than the title. However, it never names gate_create_run, the closest sibling, so an agent must infer on its own whether to delegate or create a fresh run.

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 implies the precondition (you must already hold a parent app key and run token) and establishes that the delegated run is 'narrower'. But it gives no explicit when-to-use/when-not guidance and does not route the agent away from gate_create_run, which is the real selection decision here.

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