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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses throughput limits (3 free calls/day shared across tools), cost after that ($0.005 USDC), the payment channel (in-band params._meta["x402/payment"], or card credits), the backing model (Workers AI Llama 3.1 8B), accepted transports (GET query or POST body), and the closed-label output guarantee. These are exactly the operational facts an agent needs that no annotation or schema conveys.

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?

Compact and dense with no filler, but the long pricing/payment sentence is front-loaded ahead of what the tool actually does, delaying purpose recognition for an agent scanning for capability. Every sentence earns its place; only the ordering costs a point.

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 3-parameter, fully-described-schema tool with an output schema, the description covers capability, limits, cost, transport, and model choice. Nothing needed to call it correctly or predict its cost is missing.

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 baseline is 3, but the description adds constraints the schema omits: text capped at 6,000 characters and labels constrained to 2-20 comma-separated values in single or multi-label mode. It does not document the string-typed 'multi' flag's accepted values beyond 'true', which keeps it from a 5.

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 ('Text classification: classify text ... into your own labels') plus concrete scope limits (6,000 chars, 2-20 labels, single vs multi-label) and the output guarantee ('output is always one of your labels'). This distinguishes it from near neighbors such as news_sentiment, entity_extract, or summarize, which produce their own taxonomies rather than user-supplied labels.

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?

Explicit 'When to use' clause names concrete scenarios: routing tickets, emails, or posts into your own labels. However, it never names an alternative tool or states when NOT to use it (e.g., use news_sentiment when you don't have your own labels), so the routing logic relative to siblings remains implicit.

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