chat

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

Annotated with readOnlyHint=false, openWorldHint=true, idempotentHint=false. The description adds the key behavioral detail: 'Charged in credits from the connected account', which is not in annotations. No contradiction with annotations.

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: first states the core function and output, second explains input modes and cost. Every sentence is functional, no redundancy, 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?

Although no output schema exists, the description mentions output content (reply text, token usage, credit cost), which is sufficient for a straightforward chat tool. Parameters are fully covered in schema and augmented by description.

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%, establishing a baseline of 3. The description adds value by advising when to use 'model' parameter and clarifying the choice between 'prompt' and 'messages'.

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 specifies 'Chat with a text LLM (Claude / GPT / Gemini / DeepSeek class)' and the output includes 'reply text plus token usage and credit cost'. It clearly distinguishes from sibling tools like image or audio generation.

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 provides guidance on using a single prompt vs messages array and model selection hints (e.g., 'Pass a flagship reasoning model for hard tasks'), but lacks explicit when-not-to-use guidance or direct comparison to sibling tools like 'get_generation'.

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