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

Annotations cover only the safety profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), so the description carries the interesting burden and does: it discloses that calls are paid, in USDC on Base, at $0.002 per successful call via x402. That is exactly the auth/payment context an agent must know before invoking, and it also explains why a pure inference call is flagged non-readonly.

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 tight sentences: what it does first, then when to use it, then cost. No filler, no repetition of the parameter block, and the most decision-relevant facts are front-loaded.

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 one-param tool with no output schema, the description does describe the return shape (label plus confidence score), the model, and the payment model, so an agent has what it needs to call it. The only real gap is failure behavior — what happens if payment fails or the text exceeds the limit — which is left implicit.

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?

Only one parameter and schema description coverage is 100%, with the schema already stating 'English text, up to 4,000 characters'. The description's mention of 'English text' echoes rather than extends the schema, so the baseline 3 for fully-documented params 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-ish task and resource (positive/negative sentiment of English text, with a confidence score) plus the exact model and training set (DistilBERT fine-tuned on SST-2). This cleanly separates it from generic siblings like ai_classify or ai_extract-json without opening any 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 concrete usage context — 'triage reviews, support messages, social posts and replies' — which tells the agent when this tool fits. However, it never excludes anything or names an alternative (e.g. ai_classify or ai_chat) for cases where sentiment alone is insufficient.

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