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

Well beyond the readOnly/idempotent annotations, it discloses the authorization model (project members only, 404 for non-members; company_id must equal the JWT company; admins see all exec reports, other members only those they received), error codes (400 validation_failed, 400 on kind/scope mismatch), retention (1 year), plan availability, and that test sends are excluded. This is exactly the behavioral context annotations cannot express.

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 correctly with scope and the either/or rule, but the final paragraph largely re-states the opening paragraphs (newest first, no content, one-of-the-two, limit=1 → get_summary), so a meaningful fraction of the text does not earn its place. The title is also repeated verbatim as the first sentence.

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?

There is no output schema, and the description compensates by saying rows are SummaryListItem with no sections and that paging uses next_before from the previous page. Access rules, error conditions and retention are all covered; only the SummaryListItem field set itself is left by name only.

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 80% and the enum for kind is already documented, so the schema carries most parameter detail. The description adds the cross-parameter constraint that exactly one of project_key/company_id is required and that kind must belong to the chosen scope — semantics the schema's per-field descriptions only partially convey.

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 concrete verb and resource ('the summaries that were sent, newest first'), names both scopes (project archive vs. company executive reports), and contrasts implicitly with get_summary by noting rows carry no content. An agent can distinguish this from get_summary and list_* siblings without opening a 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?

Explicitly says to give exactly one of project_key or company_id, and routes to the alternative: 'To read the newest summary of a kind call this with limit=1, then get_summary with the returned id.' It also states exclusions (settings, previews and test sends are web only), so the agent knows what this tool will never return.

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