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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds substantial context the annotations do not: a server-side rate limit of 20/hour per user, asynchronous execution semantics, the exact return shape ({"task_id", "status": "PENDING"}), and the polling workflow via `get_task_status`. It also warns this is the slow (~10-12 min) professional deep-dive. No annotation contradiction.

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 a clear '===> THE RIGHT TOOL' marker and logically ordered routing rules. It is longer than needed: the 'EXPLICITLY asks for the full report' constraint is stated twice and the options are spread across several paragraph fragments.

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 rate-limited, asynchronous, multi-minute job with an output schema present, the description supplies everything an agent needs: routing against three siblings, throttling, async return contract, and the polling follow-up. Since an output schema exists, it correctly avoids explaining the final report's contents.

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 both `query` and `delivery` are already documented by the schema, establishing the baseline of 3. The description reinforces `query` semantics via inline examples but says nothing about `delivery` channels or the delivery effect, so it does not exceed the schema.

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 (generate) and resource (research report) with clear scope: open-ended or thematic questions, extensible, multi-section. It explicitly contrasts itself with `get_latest_report` and `explore_data_catalogue`, so an agent can distinguish it from 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?

Gives explicit when-to-use ('intent is a QUESTION rather than a request for an existing report'), when-not-to-use (plain 'get me the latest report' → `get_latest_report`; exploration → `explore_data_catalogue` first), and sequencing rules ('never run both for the same question at once', 'reach for THIS deep-dive only later'). Nothing is left to inference.

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