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

Annotations declare openWorldHint=true and readOnlyHint=false, but the description adds material context the annotations cannot: the name of the external third party receiving the data, the double opt-in flow ('the user then gets an email link to confirm before the broker sees anything'), and the commission/fee arrangement. It does not address what a duplicate call does, which matters given idempotentHint=false, so not a 5.

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 action and the consent gate are front-loaded, and the quoted disclosure is long but functional since it must be shown verbatim. The closing 'Never call it on the user's behalf without that agreement' restates the earlier precondition and is mild redundancy, but it is defensible for a compliance-critical call.

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?

The workflow, consent, privacy and third-party disclosure are all covered, which is the highest-risk part of this tool. For a 28-parameter submission with no output schema, however, the description says nothing about the return (confirmation, reference, link re-send) or about which of the many optional financial fields are genuinely needed, leaving an agent under-informed before filling a large payload.

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 only 50% across 28 parameters, so the description has to carry weight, and it does partially: 'Collect their name, email and phone' maps to three of the eight required fields and the consent gate is emphasized. The other required fields (applicants, state, price, first_home) and the roughly twenty optional financial inputs get no semantic treatment beyond what the schema already says.

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 first sentence states a specific verb and destination: send the user's situation and readiness report to Goodlend Mortgage Brokers, who then contact them. That is unambiguous and no sibling tool (assess/calculate/check/list) does anything comparable. It stops short of naming a sibling or stating the boundary explicitly, which is what keeps it from a 5.

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?

Usage is tightly constrained: 'ONLY call this after you have shown the user this disclosure and they have explicitly agreed in this conversation', reinforced at the end with 'Never call it on the user's behalf without that agreement.' That is a clear precondition and a clear prohibition. What is missing is the alternative path (what to do instead when the user declines), so the agent has no named fallback.

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