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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the description only has to add operational context — and it does: the keepPolling contract, the meaning of the 'building' state, and the fact that a quote link plus price summary are returned only at 'sent.' That is genuinely useful polling behavior not derivable from annotations. It stops short of stating rate limits or what happens when the request is not found.

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?

Front-loaded with purpose, then prerequisites, then return behavior across five short sentences — appropriately sized for a polling tool. Minor redundancy: 'Returns keepPolling true while the quote is still being prepared' and '"building" is normal while the quote is prepared' cover largely the same ground.

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 read-only, idempotent status check with a full output schema, the description covers everything an agent needs: identity requirements, the full state vocabulary, the polling signal, and the terminal-state payload. Return-value details are already in the output schema, so explicitly describing the 'sent' payload is a bonus rather than a gap.

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 100%, so the baseline is 3. The description adds one real signal — that caller identity is required ('the phone or email used on the request') — but the schema lists only serviceRequestId as required, leaving the exact phone-or-email requirement slightly ambiguous between the two sources. Beyond that it adds nothing the schema does not already say.

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 ('Get the status of an existing Detritus quote request') and enumerates the possible states (received, assigned, building, sent), so the agent knows exactly what this returns. It does not explicitly contrast itself with get_quote or make_service_request, but the 'existing ... request' framing plus the required serviceRequestId makes the distinction inferable.

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 clear operational context: it is a polling tool ('Returns keepPolling true while the quote is still being prepared') and pre-empts a false alarm by noting '"building" is normal while the quote is prepared.' It does not name alternatives (e.g., use get_quote once a quote link exists) or state when-not to call it, so it falls short of explicit routing.

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