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

Adds real context beyond the annotations: a specific platform fee (CHF 0.05 per accepted call), the required quote-first sequencing, and the state transition. This is consistent with idempotentHint=true and readOnlyHint=false. It stops short of describing retry/error behavior or what classification is produced.

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 short sentences, purpose front-loaded, no filler. The 'Never:' fragment is terse but readable and earns its place as a hard boundary.

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 should say more about what a classification yields or which categories exist, and it leaves two parameters undocumented. For a 5-param money-touching mutation it is adequate but not complete.

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 60%, and the description names only quote_id, mandate_token and idempotency_key – all three already documented in the schema – while adding the useful ordering constraint. The required 'text' and 'channel_message_id' parameters get no explanation, so the description does not fully compensate for the coverage gap.

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+resource ('Classifies a customer request') and a precise state transition ('REQUEST → CLASSIFIED'), which is more than a tautology of the title. It does not, however, differentiate itself from plausibly related siblings like intent_match or assign, leaving the agent to infer the boundary.

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?

Provides one workflow prerequisite ('quote first, then send quote_id, mandate_token and idempotency_key') and one explicit exclusion ('Never: Set an emergency tariff'). It never states when to prefer this tool over siblings such as intent_match or assign, so routing guidance is only partial.

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