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

Annotations already cover read-only, idempotent, non-destructive, so the description is free to add the things annotations cannot: that it returns subject and body, that details must be numbers and short labels, and that contact details are refused. The walk-line suppression rule ('an offer above it is not drafted') lives only in the nested schema, not the description, which is the one behavioral gap.

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?

Two sentences, front-loaded with the action and the enumeration, with the input constraint second. Dense but no filler; slightly long parenthetical could be trimmed but every clause carries information.

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 tool with a 16-field nested object at 50% schema coverage and no output schema, the description should clarify per-kind required details and the walk-line suppression rule. It covers the return value and the contact-detail refusal, but leaves the kind-to-details mapping and the walk-line behavior undocumented.

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 50% across a 16-property nested object, so the description carries real burden. It adds one useful constraint -- details are numbers and short labels and contact info is rejected -- but never explains which detail fields each of the six kinds needs or expects, which is the key decoding problem for a nested-object param.

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 concrete action (fills a template, returns subject and body) and enumerates all six template kinds, so an agent knows exactly what the call produces. It does not distinguish itself from siblings like desk_script or check_quote, which could plausibly also involve dealer communication, so it stops short of 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 implied by the template list (you'd call this when you need to draft one of those six emails), but there is no explicit when-to-use or when-not-to-use guidance relative to siblings such as desk_script. An agent must infer the boundary from the template names alone.

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