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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real operational context on top: the call is free, it requires the suppressions:read scope, results are point-in-time ('as of now'), and it discloses the default audience composition constraint under PECR. Nothing here contradicts the annotations.

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?

Front-loaded with purpose, then usage, then cost/auth, then compliance caveats — a sensible ordering with no filler sentences. The closing PECR/legitimate-interests sentence is longer than the invocation itself needs, though it does supply non-obvious audience-scope context.

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 single-parameter read tool with an output schema and full annotations, the description covers the remaining gaps an agent needs: cost, required scope, point-in-time semantics, batch limit, and what to do with the results. Return-value shape is correctly left to the output schema.

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?

The schema documents the id format and the maxItems cap, but the description adds meaning the schema cannot: only *delivered* records can be checked, and the status is evaluated as of the current moment rather than historically. It does not, however, explain what happens if non-delivered or unknown ids are passed, leaving one behavioral edge undocumented.

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 (checks suppression status of delivered records), plus the scope limits that matter: by record id, up to 1,000, as of now, and it names the suppressing lists. That distinguishes it cleanly from siblings like report_objection or get_compliance_receipt.

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 an explicit cadence ('Use it before every send'), the reason for that cadence ('objections reach records after delivery'), the action to take on results ('Leave suppressed records out of the send'), and routes the adjacent case to a named sibling ('call report_objection when someone objects'). Both when-to-use and the alternative are stated.

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