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

Annotations cover mutation/idempotency safety, but the description adds crucial non-obvious behavior: the token is shown only in this response (must be persisted immediately), it is write-only for sending feedback, safe to embed in bundles/binaries, and creation targets the org's default project. These are exactly the traits an agent cannot infer from annotations or schema.

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?

Roughly five sentences, front-loaded with the action and return value, then parameters, then the critical write-it-down warning and auth/skill prerequisites. No filler sentences.

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 two-parameter creation tool with no output schema, the description covers the return value (token), its one-time visibility, its security properties, the project scope, and the auth requirement — everything needed to invoke 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?

With 0% schema description coverage, the description fully compensates: `name` is defined as the app's name, and `allowedOrigins` is defined as every browser origin with concrete format examples and an explicit omission rule for non-browser apps.

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+scope ('Create a feedback channel for one app and return its feedback token'), making it clearly distinguishable from the sibling send_feedback which presumably posts feedback rather than creating a channel.

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 strong context: requires an organization admin, instructs reading the `install-feedback` skill before the first call, and explains when to omit allowedOrigins (non-browser apps). It does not explicitly contrast with alternatives like send_feedback, but the prerequisite and gating guidance is clear.

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