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

Annotations declare readOnlyHint=false and destructiveHint=true, and the description adds real behavioral context beyond them: the estimate leaves the 'sent' state, an accepted one can later become an invoice, and confirm=false yields a preview rather than a change. It does not describe permissions or what the preview contains, which keeps it out of the top band.

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 tight sentences, the core action and its state effect are front-loaded, and the confirm requirement is called out last where it belongs. No filler.

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 4-param mutation tool with no output schema but strong annotation coverage, the description covers the state transition, the preview behavior, and the domain outcome. It leaves minor gaps (permissions, preview contents) but nothing critical to invoking it correctly.

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 75%, so the schema already documents 'by', 'confirm', and 'invoiceId' in detail. The description reinforces the confirm-preview semantics and names the accepted/declined values, but adds little beyond what the schema and enum already convey. A baseline 3 is appropriate.

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: records a client's accept/decline answer on a sent estimate, with the responder's name. It also hints at the downstream relationship ('an accepted one can become an invoice'), which helps separate it from siblings like convert_estimate_to_invoice. It stops short of naming a sibling directly, so it is clear but not maximally differentiated.

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?

Gives clear context: the answer is captured from a phone or email response, and it explicitly states the operational requirement ('Needs confirm: true; without it the result is a preview'). It does not name alternative tools or state when NOT to use this one, but the when-to-use context is solid.

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