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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. However, the description adds only a broad entity list and tenant scoping, not meaningful behavioral context such as what the export generates, whether it returns an existing artifact, or what side effects may occur. 'Operate on' is too generic to be transparent about behavior.

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 description is short, but it is under-specified rather than concise. It front-loads no actionable specifics and uses one generic sentence to cover an entire domain, which forces the agent to guess the actual operation.

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 13 parameters, zero required fields, nested objects, and a low-coverage schema, the description is far too incomplete. It does not indicate which parameters are needed for an export, what the inputs mean, or how the operation should be invoked. Even with an output schema present, the agent lacks enough information to correctly assemble a call.

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 15%, with only tenant_id and adapter_id described. The description does not explain any of the 13 parameters, such as format, estimate_id, document_id, query, bridge, approval, or idempotency_key, nor how they relate to the export operation. With such low schema coverage, the description was expected to compensate, but it provides no parameter-level meaning.

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 uses the vague verb 'Operate on' and lists a broad collection of resources (drafts, lines, versions, documents, exports, policy receipts) without stating the specific operation. It does not clearly say that this tool exports an estimate, nor does it distinguish itself from siblings like estimator_estimate_create_draft or estimator_estimate_convert_to_invoice.

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 guidance about when to use this tool versus alternatives, no exclusions, and no mention of sibling tools or conditions. The phrase 'tenant-scoped' gives a contextual boundary but does not help an agent decide between this export tool and the many other estimator_* tools.

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