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

Goes well beyond the readOnly/openWorld annotations by disclosing the exact per-call cost ($0.002 USDC via x402 across Base, Solana or Arc), that failed calls are not charged, per-item character and batch-size limits, and the fact that the model judges wording rather than truth. These are precisely the operational facts an agent needs before invoking a paid endpoint.

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?

A single dense sentence ordered from capability to limits to model to caveat to pricing, with no filler. Every clause carries information the agent can act on.

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?

An output schema exists so return shape need notbe explained, and the description covers the remaining unknowns: capacity limits, model provenance, semantic caveat and cost/charging behavior. Nothing material for correct invocation 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 description coverage is 100%, so both parameters are already documented in structured data; the description restates the same 2,000-character and 20-item limits. It adds only a mild clarification that the two parameters are alternatives ("one text, or up to 20"), which the schema does not express.

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 (sentiment of one text or up to 20), names the exact output labels (POSITIVE/NEGATIVE with confidence) and the underlying model (DistilBERT SST-2). It does not explicitly distinguish itself from adjacent siblings such as text_tone, classify or moderate, so an agent must infer the boundary from the label set alone.

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?

"Best for short English text" gives a clear usage context and implicitly excludes long or non-English input, and "measures the wording, not whether the statement is true" warns against a common misuse (fact-checking). No alternative tool is named, so the exclusion side is only implied rather than explicit.

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