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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the bar is lower. The description adds genuinely useful context not in the schema: that results are grouped per KP's review and each group carries a proposal, count, total and examples. No pagination or size behavior is mentioned, which keeps it from a 5.

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 compact sentences, return shape described first and the action directive second, with no filler. The first sentence is dense and slightly awkward ('grouped like KP's review'), but no sentence is wasted.

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 carries the return-shape burden and does describe the group fields and examples. What is missing is minimal: no note on volume/limits or what happens when there are zero open questions, but an agent has enough to call it correctly and know what to do next.

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%, with job_token, file_id and language all documented in-schema including the file_id fallback case. The description adds nothing parameter-specific, 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 and resource: lists bookings that could not be assigned to an account with certainty, and describes the grouping (booking type, counterparty, single booking). This is clearly distinct from siblings like get_preview or download_result, and an agent can tell what it returns without opening the 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?

The closing sentence 'Answer them with answer_questions' explicitly routes the agent to the correct follow-up tool. It does not state exclusions or prerequisites (e.g. job must be finished), but the pairing with answer_questions is clear enough to act on.

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