Records inside one aggregate report

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

Annotations already cover the safety profile (readOnly, non-destructive), so the description's added value is real: it discloses that third-party strings are length-capped (lossy output), caps results at 50 rows, and defines the truncation/next_offset contract. That is genuine behavioral context beyond the structured fields, though it omits error behavior for an invalid id.

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?

Three tight sentences, each carrying distinct information: what is produced, what is degraded, and how to page. The pagination rule is stated last where it is needed, 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?

With no output schema, the description usefully enumerates the returned row fields (source, count, alignment, disposition, identifiers) and the truncation flag, so the agent knows the shape of the result. The remaining gap is routing: it never says how to obtain the report id or when this beats query_records.

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% and both parameters are documented there, so the baseline is 3. The description only reinforces the schema by explaining the next_offset → offset round-trip, adding no syntax or format detail the schema lacks.

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: re-parses one aggregate XML into per-record rows, and enumerates the row fields. Clear what it produces, though it never names which sibling to use first (list_aggregate_reports) to obtain the id it requires.

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?

Usage is implied by 'one aggregate XML' plus the pagination instruction ('when truncated is true, pass next_offset back as offset'), which tells the agent how to continue an existing sequence. It gives no when-to-use vs query_records or list_aggregate_reports, and no preconditions beyond the pagination loop.

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