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

No annotations are provided, so the description carries the burden. It discloses that the tool is a read-like classification operation, that it has a quota unit per import, and that previously seen descriptions are served from a shared cache free. It also warns not to send amounts or dates. It doesn't state whether the operation is idempotent or whether it mutates state, but the cache/quota note gives meaningful behavioral context.

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, each earning its place: what the tool does, what to send/not send and the follow-up step, and the quota/cache behavior. The most important usage constraint is front-loaded. No fluff.

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 tool with no output schema and no annotations, the description covers the key operational details: input constraints, follow-up step, quota, and caching. It doesn't describe the exact format of the returned categories or how to handle errors, but the description is sufficient for an agent 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 coverage is 100%, so the schema already documents both parameters. The description adds value by explaining the purpose of tradingType (resolving ambiguous merchants) and by clarifying that descriptions are raw strings, one per transaction. It also adds the constraint to send only descriptions, not amounts or dates, which is not in the schema. This goes beyond the baseline 3.

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?

The description states a specific verb ('Categorise'), a specific resource ('bank-statement transaction descriptions'), and a clear outcome (mapping to fixed vocabulary for balance sheet lines). It also distinguishes itself from siblings by naming totals_to_figures as the follow-up step, and the fixed vocabulary examples (sales, software, owner-in) make the purpose concrete.

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 description explicitly says when to use this tool: send description strings only, never amounts or dates, and then call totals_to_figures. It also gives a quota/caching note that helps an agent decide whether to call it. This is strong usage guidance beyond the schema.

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