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

Beyond the annotations, it discloses two important behavioral facts: a verification code is dispatched to the shopper as a side effect, and prices come from a test environment and cannot be bound online. It also notes the flood zone is derived from the address rather than supplied. It stops short of saying what a repeat invocation does (annotations mark it non-idempotent), which would be the last piece of context.

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-loads the trigger condition and the action, then moves to prerequisites and parameter detail in a logical order with no filler sentences. It is dense but every clause carries information; the only cost is that the parameter guidance is packed into one long paragraph that is slightly harder to scan.

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 multi-step, 13-parameter mutation with no output schema, the description covers the prerequisites, the side effect, the coverage ranges, and the downstream tool to call. The remaining gaps are the verify_by channel choice and repeat-call behavior, which are moderate rather than blocking.

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% across 13 parameters, so the description has to carry the load, and it does for the non-obvious ones: building_coverage bounds (20000–5000000) with guidance on using rebuild cost and the 250000 federal maximum, contents_coverage bounds (0–1000000), and the origin of consent_version. Names, address, and contact fields are self-evident, but verify_by (sms/email) and assistant_name are never mentioned despite being agent-selectable.

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?

Names a specific verb and resource ('Starts a flood estimate') and adds a concrete effect ('sends the shopper a 6 digit verification code'). The opening line scopes it to Tennessee flood quotes, which cleanly separates it from start_life_quote, start_quote, and get_flood_quote.

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?

Explicitly states the triggering user intent and both hard prerequisites: check_eligibility must have returned eligible, and the shopper must have read the consent text and agreed with the consent_version from that call. It also gives forward sequencing ('After verify_contact, call get_flood_quote'), so the agent knows where this sits in the flow.

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