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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: required agent key auth, the poll-rate limit to avoid hammering the endpoint, and the state-to-action mapping that determines what the agent should do next.

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?

Dense and front-loaded: the mode switch comes first, then the status vocabulary, then the poll limit and the action rules. Telegraphic phrasing, but each clause carries operational information an agent needs and nothing is wasted.

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?

With no output schema, the description still supplies everything needed to call and act on the tool correctly: the status enumeration, auth requirement, polling constraint, and the follow-up tool for each terminal state. Nothing material is missing for a single-optional-param read tool.

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 coverage is 100% and the schema already explains that ask_id is the id returned by ask_human or register. The description goes beyond that by spelling out the conditional semantics — one ask with the id versus the full list without it — which is real added meaning over the schema one-liner.

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 and resource ('your asks for money') and disambiguates the two modes explicitly: with ask_id returns one ask (GET /asks/{id}), without returns all (GET /asks). An agent can distinguish this from siblings like my_status or ask_human without opening the schema.

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 concrete when-to-use guidance and branches on state: 'settled or approved: call my_status and claim', 'declined or expired: stop, and do not ask the same human again for 7 days'. It names the alternative tool (my_status) and imposes an explicit polling cadence of at most once per 30–60 seconds.

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