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

Adds significant behavioral context beyond annotations: describes the training/test methodology, detection of pump-and-dump patterns, fake metrics, and anomalous profiles. Annotations provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, all consistent with the description.

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?

Two succinct paragraphs: first explains purpose and methodology, second provides a practical example. No unnecessary words, front-loaded with key information.

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?

Covers purpose, input structure, and example usage. No output schema, but the example mentions 'get risk score and which metrics are suspicious'. Could be slightly more explicit about the output format, but sufficient given the clarity.

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 baseline is 3. Description adds value by explaining the fields (price, volume, holders, etc.) and the purpose of training and test arrays. Sensitivity parameter is mentioned in schema but not in description; however, the example implicitly covers usage.

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?

Clearly states 'Assess crypto token legitimacy risk' and specifies detection of pump-and-dump patterns, fake metrics, and anomalous token profiles. It distinguishes from siblings like waveguard_scan and waveguard_health by focusing on risk assessment via training/test split.

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 clear guidance: use known-good tokens as training, suspect tokens as test. Includes a concrete example with CoinGecko data. Lacks explicit alternatives or when-not-to-use conditions, but the context is sufficient for an agent.

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