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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, yet the description still adds substantive behavior: the permission required (send_planner.view), the read-only limitation, the polling-until-ready workflow, and the ordering/capping of exceptions (up to 25, worst first). None of this is derivable from the structured fields.

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 first sentence is a long but dense enumeration of return contents and each clause carries information; the remaining sentences front-load the default behavior and the polling case. Slightly heavy in a single sentence, but no filler and the primary instruction comes first.

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?

With no output schema, the description must carry return-value disclosure, and it does so thoroughly while also covering auth requirements and the read-only boundary. Nothing an agent needs to call this correctly and interpret the response is missing.

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 100% for the single parameter, so the baseline is 3, but the description adds real meaning: what omission defaults to (latest ready working plan) and why you would supply an id (to follow an externally started plan, polling for status). This tells the agent more than 'The send plan id' alone.

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 ('Get a send plan') and then enumerates exactly what comes back: status, data as-of time, per-network totals (units, SKUs, cases, capacity), top exceptions, 2-day reach, and the 5 lowest-reach fast sellers. An agent can distinguish this retrieval tool from explain_send or api_read without opening the schema.

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 explicit routing rules: omit send_plan_id to get the latest ready working plan, or pass an id to follow a plan started elsewhere and poll until 'ready' or 'failed'. It also names the boundary condition ('this server is read-only and cannot start a plan'), pointing the agent to the app or POST /api/send-plans for creation.

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