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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds meaningful behavioral context: it returns 'polarity plus the terms that drove it' and explains the crypto-specific tuning, which goes beyond the structured hints. It also clarifies that the tool does not perform lookups, adding transparency about its scope.

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?

The description is front-loaded with the core purpose and then adds context in a logical flow. The second sentence includes an illustrative comparison to general models ('wagmi') which, while vivid, is slightly verbose. Overall, every sentence contributes value, and the structure is clear without excessive length.

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 one parameter and no output schema, the description fully covers what the agent needs: what it does, what input to provide, what it returns (polarity and terms), and its specialization. The lack of an output schema is compensated by the explicit mention of the return contents. No critical information 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?

With a single parameter 'text' and 0% schema description coverage, the description compensates by calling it 'arbitrary text you supply' and clarifying it is not a lookup. This adds some meaning beyond the bare name, but it stops short of specifying format, length limits, or examples. For a simple parameter this is adequate but not thorough.

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 opens with a clear verb-resource pair: 'Score any text for crypto sentiment.' It specifies the domain (crypto), the input (arbitrary text), and the tuned nature, making it distinct from the many get_* lookup siblings. No ambiguity about what this tool does.

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 states 'Takes arbitrary text you supply — it does not look anything up,' which sets a clear context for when to use it: for analyzing user-provided text rather than querying data. It implies it is not for retrieving stored sentiment, but it does not name an alternative tool like get_aspect_sentiment. Still, the usage boundary is clear enough.

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