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

Annotations already declare readOnlyHint and idempotentHint, so the description's additional value is the polling behavior and the fact that it may return early with timed_out=true, followed by a safe retry. This adds context beyond the structured annotations and is consistent with them.

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 core purpose and followed by a brief retry instruction. Every word earns its place; no fluff or redundancy.

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 simple polling tool, the description covers the essential behavior (poll until state change or timeout) and the retry action on timeout. It does not explain the full return structure, but without an output schema and given the simplicity, this is sufficient. Minor gaps remain about auth parameter selection, but those are partially covered in the schema.

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 description references 'timeout expires,' which arguably maps to the timeout_seconds parameter, but it does not explain the undocumented session_id parameter or clarify the relationship between url, session_id, and access_token. With only 60% schema description coverage and no compensating detail in the description, parameter semantics are under-served.

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 tool polls until the intake leaves processing or timeout expires, which is a specific verb (poll) with a resource (intake) and termination condition. This distinguishes it from siblings like get_intake_state that likely return the current state without blocking.

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 gives a clear retry instruction for timeouts ('If timed_out is true, call wait_for_next_action again'), which is useful. However, it does not explicitly contrast with alternatives like get_intake_state or state when not to use this tool, so usage context is only implied.

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