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

Annotations only declare the safety profile (readOnly, idempotent, non-destructive). The description adds the missing operational context: the call blocks on a lookup that usually takes under 30 seconds, it may return 'collecting' and require immediate re-polling, and it can fail into a 'manual' state. That is exactly the behavior an agent needs to handle it correctly.

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?

Four short sentences, front-loaded with what is returned and the latency expectation, then ordered by status branch. No filler and no repetition of the schema or annotations.

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?

There is no output schema, so the description carries the return-value burden and does it by enumerating the meaningful status states and what each means. Combined with the stated latency and the handoff to submit_property_details, an agent has everything needed to invoke and act on the result.

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% and quote_id is never mentioned in the description, so the agent must infer that quote_id ties to the quote produced by start_quote/select_quote. With a single obvious parameter the gap is minor, but the description adds nothing about format or provenance.

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: returns what DwellQuote found about the property. It also names submit_property_details as the downstream sibling, giving the agent contrast. It stops short of explicitly contrasting with get_quotes or select_quote, but the action is unambiguous.

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 explicit branching guidance for each status value: 'collecting' means call it again right away, 'ready' means show facts and ask for confirmation, 'manual' means collect fields from the user, then call submit_property_details. Each case names the concrete next action and the tool to use.

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