Refresh catalog

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

With no annotations, the description must carry the behavioral burden. It does so by explaining cache bypass behavior, failure fallback ('the last good catalog keeps being served'), and the reported state ('servedStale is reported as true'). This is strong but not exhaustive; it omits any potential side effects beyond cache behavior.

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?

Three concise sentences, each earning its place: what it does, when to use it, and what happens on failure. The most important action is front-loaded, and there is 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?

For a no-parameter cache refresh helper, the description covers the essential context: purpose, trigger condition, and failure behavior. It does not specify the full success return shape, but the servedStale reference gives the agent a useful signal about the report format.

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?

The tool has zero parameters, so the input schema leaves nothing to document. Per baseline guidance, a 4 is appropriate since there is no parameter semantics gap for the description to fill.

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 uses a specific verb ('refresh') and resource ('models.dev catalog'), and states the exact mechanism ('bypassing the in-memory cache'). This clearly distinguishes it from the sibling query-oriented tools like list_providers and find_models.

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?

'Use if you suspect the data is stale' provides an explicit condition for invoking the tool. It does not discuss when not to use it or name alternatives, but given the tool's unique refresh role among siblings, the guidance is sufficient.

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