Deliver a report to recipients

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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds genuinely useful behavior beyond that: the write is gated on confirm: true, there is no server-side dry run, and unconfirmed calls return a request preview. It stops short of saying what delivery actually does (e.g., emails recipients), whether it is irreversible once sent, or any rate/recipient limits.

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 endpoint, then the critical WRITE gating constraint. The 'WRITE:' label and the parenthetical about the missing dry run make the key risk scannable with 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 mutation tool that reaches outside the system (openWorldHint) with no output schema, the description covers the safety gate and preview-return behavior but omits the delivery mechanism, irreversibility, and recipient constraints. It is enough to avoid an accidental send, but not enough to predict the outcome of a confirmed 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 coverage is 50%: confirm and idempotencyKey already carry schema descriptions, and the description merely reinforces the confirm gate rather than adding new meaning. The undocumented parameters (`id` as report identifier and the nested `body.recipients` semantics, including the 1–20 limit and what a recipient value looks like) are left unexplained in both places, so the description does not compensate for the coverage gap.

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?

Names a specific verb and resource ('Deliver a report to recipients') and pins it to the endpoint POST /v1/reports/{id}/deliver, so an agent can identify the action without opening the schema. It does not explicitly distinguish itself from nearby siblings such as reports_listDeliveries, reports_generate, or reportSchedules_create, so the differentiation is only implicit.

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 gives one strong operating condition — nothing is executed unless confirm: true — which effectively tells the agent to preview first. However, it offers no guidance on when to use this versus alternatives (scheduled delivery via reportSchedules_create, or sharing via shareLinks_create), and no prerequisites or exclusions are stated.

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