Generate a report for a client and period

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

Annotations only say readOnlyHint=false and openWorldHint=true, so the write nature and external side effects are already flagged. The description adds real value beyond that: it marks the operation as WRITE, explains the confirm gate, notes there is no server-side dry run, and states that omitting confirm returns a request preview. It stops short of describing what gets created (a report record, an async job?) or whether repeat calls with the same idempotency key are safe.

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 short sentences, zero filler, and the critical safety information (WRITE, confirm gate, no dry run) is front-loaded immediately after the purpose statement. Nothing is repeated or padded.

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 no-output-schema write tool with a nested body, the definition covers the highest-risk unknowns: that it writes, that it will not execute without confirm, and that a preview is returned otherwise. The remaining gap is what the successful response contains (report id, status, async completion) and how templateId relates to reportTemplates_list.

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 67%, with confirm and idempotencyKey already documented in the schema itself, and the description merely restates the confirm behavior. The nested body fields (clientId, from, to, templateId, title) receive no semantic explanation in either place, so the description adds little meaning beyond the structured fields.

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 ('Generate a report') plus the scope ('for a client and period') and even the endpoint POST /v1/reports. It does not, however, distinguish itself from closely related siblings such as reports_renderPdf, reports_renderHtml, or reports_deliver, so an agent must infer that this creates a report record rather than rendering or sending one.

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?

The description does give one concrete usage rule: the call is a no-op unless confirm: true is supplied. That is genuinely useful gating. But it offers no guidance on when to choose this tool over reports_renderHtml/reports_renderPdf/reports_deliver, nor any prerequisites such as a valid templateId or client permissions.

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