refresh_models

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

With no annotations, the description carries the full burden. It discloses that previous model lists are discarded and replaced (destructive behavior), that only providers with API keys are fetched, and that other providers keep their existing list. It also mentions the optional ping test, but does not cover all potential side effects like rate limits or network latency.

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 main purpose, followed by details and Args. It is well-structured and not overly verbose, though it could be slightly more concise by merging some sentences.

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?

Given the output schema exists (so return values are handled), the description covers all necessary aspects: what the tool does, when to use it, parameter details, and optional post-refresh actions. It is complete for the tool's complexity.

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 0%, so the description must compensate. It includes an explicit 'Args' section that explains each parameter in plain language: provider (optional), run_ping (triggers ping test), ping_limit (max models to ping). This adds significant meaning beyond the schema's type/name only.

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 verb 'fetch and replace' and the resource 'model lists from configured providers' with specific examples (openrouter, nvidia, groq). It distinguishes from siblings like list_models (which likely just lists) and scan/get_fastest (which are for discovery after refresh).

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 clear guidance: 'Only providers with API keys are fetched' and 'Use this to get the current catalog, then call scan() or get_fastest() for discovery.' It implies when to use but does not explicitly state when not to use or provide exclusions.

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