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

The annotations declare readOnlyHint=false and idempotentHint=false, but the description (matching the GET /v1/reports/history endpoint) presents a read-only, repeatable listing — 'List...', 'Re-fetch a report link', 'Free to call'. The description's implied read-only, idempotent profile directly contradicts those two 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 the purpose in the first sentence, then layers on lifecycle, cost, and pagination. Dense but every sentence earns its place; only slightly long for a two-optional-param listing call.

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?

An output schema exists, so return values need not be restated, and the description covers the non-obvious operational facts: 24h purge, `expired: true` with now-dead URLs, `retain_days`, cost, and the limit range. Minor gap: it never mentions the compact-mode `fields`/`precision` behavior present in the 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?

Schema description coverage is 100%, so the schema already documents `fields` and `precision`; the baseline is 3. The description adds a `?limit=` (1–50, default 10) param that is absent from the schema, but says nothing about the two compact-mode params that are actually in the schema, so it neither compensates nor explains.

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 (List) and a precisely scoped resource (the calling key's most recently generated PDF reports) and even enumerates the returned fields (type, size, page count, language, timestamps, url). Among the many reports_* and render_* siblings, it is immediately identifiable as the export-history listing tool.

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 two concrete use cases (re-fetch a report link while it lives, or surface recent exports in a dashboard) and the retention condition that governs validity. It does not name or exclude a sibling (e.g., the reports_generate tools), so the routing guidance is clear but not complete.

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