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

No annotations are supplied, so the description carries the full burden, and it does disclose the single-invocation constraint and the user-facing messaging contract, including suppressing qualification talk. What it omits is server-side behavior: whether this creates or updates a record, what happens on partial data, what errors look like, and whether smsConsent triggers downstream texting. Those gaps keep it below 5 for an unannotated mutation.

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?

Three short sentences, front-loaded with the action, then the trigger, then the messaging constraints. Every sentence carries a distinct instruction and nothing is repeated from the schema or title.

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 9-parameter unannotated write tool with no output schema, the description covers the two hardest things an agent can get wrong: when to fire and what to tell the user. The remaining gap is how to populate the nested answers and attribution objects, which is left entirely to schema field names. That is a real but bounded omission given the schema does define those nested shapes.

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 only 44% across 9 parameters including two nested objects, and the description adds no parameter-level meaning at all. 'The person has confirmed their details' hints that the contact step supplies name/email/phone, but the answers object, attribution, medium, and smsConsent are left entirely to the schema. With low coverage the description needed to compensate and does not.

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 opens with a specific verb and resource: 'Save a completed free consult application.' Combined with the precondition against get_free_consult, an agent can tell this is the write/submission step in the consult flow and distinct from the read-only siblings. It stops short of saying what saving actually produces (a lead, a coordinator task), so it is clear rather than exhaustive.

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?

Explicit sequencing: call this once, only after get_free_consult has returned the contact step, and only after the person has confirmed their details. That names both the trigger and the gating condition, and the 'once' instruction prevents duplicate submissions. It also gives explicit do-say/don't-say rules for the follow-up message.

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