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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. The description adds the useful state fact that the object is created as a *draft* (not sent) and that it carries priced line items. It says nothing about required permissions, side effects on the project, or whether duplicates result from retries, which would be valuable given non-idempotency.

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?

One front-loaded sentence with no filler; the verb and scope lead. It is on the terse end for a destructive 8-parameter tool, but nothing is wasted.

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 destructive, non-idempotent create with an 8-parameter schema, a nested item array of up to 100 entries, low schema coverage, and no output schema, the description is too thin. It omits the draft lifecycle (needs send_estimate to deliver), the title requirement, and any hint about returning an id for follow-up calls like add_estimate_items.

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?

Coverage is 38%, so the description must carry weight. It explains the two creation modes (project vs customer) and that line items are priced, which clarifies the items/unit_cost relationship. But exclusions, inclusions, expire_date, and description are undocumented in both schema and prose, and the required title (the only required param) is not called out.

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 specific verb and resource ("Creates a draft estimate") and scopes it to two targets, "on a project or for a customer," which maps cleanly to project_id/customer_id. It does not differentiate from adjacent create tools (create_change_order, create_invoice) or from follow-ups like add_estimate_items/send_estimate, but the core action is unambiguous.

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?

There is no when-to-use guidance and no named alternatives. The word "draft" is the only implicit signal, hinting the estimate is not finalized or sent (unlike send_estimate), but the agent must infer that on its own. Sibling tools such as add_estimate_items and update_estimate are never mentioned.

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