Report as data

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds one real behavioral trait beyond them – that long reports come back paged – but says nothing about caching behavior (the `fresh` flag exists in the schema) or the shape of the returned JSON.

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 short sentences with no filler; the core capability is front-loaded and the paging/export escape hatch follows immediately.

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 read-only reporting tool with a fully documented schema and clear sibling routing, this is close to sufficient. The one gap is the return value: with no output schema, 'as the JSON' is vague about structure, and report_key/date_from being mandatory is left to the schema alone.

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%, so every one of the 7 parameters is already documented, including the nested filters object and its tie to stats_report_metadata. The description only adds meaning for `page` (paging) and nothing for report_key, date range, time_span or fresh, so the baseline 3 applies.

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+resource: it returns one report as JSON, scoped to a single report as rendered in the panel. It's clearly not the catalog/metadata tools and not the file exporter, though it never mentions the required report_key/date range in prose.

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 alternative route: for long reports use paging via `page`, or use report_export for the whole report as a file. That's clear when-to-use-what guidance, but it doesn't point to stats_report_catalog/stats_report_metadata as the prerequisite source of report_key and filters.

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