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

Annotations declare it is a mutation (readOnlyHint=false) that is idempotent, and the description adds substantial context beyond that: it stages an offer without collecting payment, does not begin carrier bind follow-up, depends on preserved MCP session state or a bearer fallback, and requires the token never be shown to the shopper. These are meaningful behavioral constraints for a mutation tool. It does not describe error or timeout behavior directly, though the idempotency_key schema covers replay.

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 purpose is front-loaded in the first sentence, which is good, but the remaining prose is long and convoluted ('a preserved host usually only needs uid,' 'Coverage Cat prefers to keep follow-up authorization in the hidden MCP shopper session'). Several clauses earn their place (payment and bind exclusions, session fallback), yet the phrasing is inefficient and would benefit from tighter structure.

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?

An output schema exists, so return values need no explanation, and the annotations carry the safety profile. The description fills the remaining gaps an agent needs: prerequisites (session state or fallback token), scope limits (no payment, no bind yet), and the intended next step. It is largely complete for this step of the flow, with only minor omissions around failure handling.

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 only 40% schema description coverage, the description usefully compensates: it explains uid ('a preserved host usually only needs uid'), that intake_access_token is an optional fallback taken from the previous successful response, and that selection_token is the value returned by the prior step. It does not explain selection_confirmed (const true) or idempotency_key, though the latter is well-documented in the schema itself.

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 states a concrete action (continue the homeowners flow after quotes are ready and stage the exact selected offer for a final bind approval in chat), which is a clear verb-plus-outcome for the select step. It distinguishes itself from the bind step by stating it 'does not start carrier bind follow-up yet,' differentiating it from homeowners_consumer_bind and umbrella_consumer_select. The core purpose is present but somewhat buried under session-state guidance, so it is clear rather than maximally sharp.

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?

It gives real when-to-use context: this is the follow-up after prefill/quotes are ready, and it names the fallback path (retry with the latest intake_access_token) plus the anti-patterns to avoid (raw HTTP, asking the shopper for credentials). It implies the bind step follows but never names homeowners_consumer_bind explicitly, so routing to the next sibling is left to inference.

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