chat

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

The description goes beyond the readOnlyHint annotation by disclosing that prompts are routed to external AI models (privacy-relevant), that conversation memory is maintained, and that it supports file context embedding and multi-turn threads. This adds behavioral context not present in the annotation, though it doesn't mention potential rate limits or data retention specifics. No contradiction with the annotation.

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 'Multi-model AI gateway,' and each phrase adds value: provider list, memory, file context, images, multi-turn. No fluff or redundancy. The description is tight while covering all key capabilities.

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?

This is a complex tool with 7 parameters, but the schema carries detailed parameter semantics, so the description only needs a high-level overview. It provides that overview without covering output format or explicit alternatives, yet the sibling names (listmodels, dump_threads) and schema guidance fill those gaps. Slightly more could be said about return behavior, but the description is sufficiently complete for an entry point.

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%, with each parameter already having detailed descriptions (e.g., temperature recommendation, model selection guidance, continuation_id semantics). The description mentions capabilities like file context and multi-turn threads, but these are already reflected in the parameter descriptions, so it adds no net new parameter meaning. Baseline 3 is appropriate.

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 clearly states the tool is a 'Multi-model AI gateway' that 'routes prompts to external AI models,' listing specific providers and capabilities like conversation memory, file context embedding, and multi-turn threads. This distinguishes it from siblings (listmodels, dump_threads) which are about listing models and dumping threads, not running prompts.

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?

Usage is implied: the tool is for sending prompts to external AI models. However, the description does not explicitly state when to use this tool versus alternatives like listmodels or dump_threads. The schema's model parameter mentions using listmodels when no model is provided, but that guidance is outside the description, so the description itself only offers implied context.

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