anthropic_create_message

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

No annotations provided, so description carries full burden. Only states 'send a message', implying mutation. Does not disclose rate limits, authentication details (beyond schema), error handling, or response behavior. Minimal behavioral insight.

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 sentences, front-loaded with verb and resource. Efficient but 'Useful for...' could be integrated or shortened. No redundancy.

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?

Tool is moderately complex with many parameters. No output schema, yet description omits response format, error handling, and authentication details. Leaves significant gaps for an agent to successfully invoke and handle the tool.

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 has 10 parameters with 60% description coverage. Description adds no additional meaning to parameters (e.g., difference between 'prompt' and 'messages'). Does not explain optional vs required beyond schema. Fails to compensate for undocumented parameters like temperature, top_p, top_k.

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?

Clear verb 'send a message' and specific resource 'Anthropic Messages API (Claude models)'. Distinguishes from sibling 'anthropic_list_models' by specifying it's for sending, not listing.

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?

States it's 'useful for agents that need to call Claude programmatically or compare model outputs', providing clear context. No explicit when-not or alternative tools, but the context is sufficient to guide selection among siblings.

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