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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description layers on real operational facts: one statement import equals one quota unit and cached descriptions are free. It stops short of stating the exact return shape (e.g. whether categories come back one per input string), so it is strong but not exhaustive.

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 sentences, all load-bearing and front-loaded: what it does, what to send, what to do next. No filler or repetition of the title.

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 burden and does indicate that categories are returned per description, enough to reconstruct the workflow. It could be slightly more explicit about the mapping result (one category per input string, unmatched handling), which is the only remaining gap for a 2-parameter tool.

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 already 100%, so the baseline is 3. The description adds meaning beyond the schema by constraining what descriptions must and must not contain, and it frames tradingType's ambiguity-resolution role; it does not, however, add syntax or cardinality guidance beyond what the schema says.

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 (categorise) and resource (bank-statement transaction descriptions) plus the target vocabulary. It also names the downstream sibling totals_to_figures, so the agent can place it in a workflow without opening another 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 input constraints (send description strings only, never amounts or dates), the required follow-up step (sum amounts per category yourself, then call totals_to_figures), and cost context. The routing to both the next tool and the schema-level lookup_company hint leaves little to infer.

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