refresh_cache

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

With no annotations, the description carries the full behavioral burden, and it does disclose meaningful traits: it operates on ALL configured subtrees, it forces an immediate re-crawl, and it bypasses TTL and version checks. It does not state permission requirements, whether the call blocks until completion, or the cost/rate-limit implications of a full re-crawl, leaving real gaps.

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?

A single front-loaded sentence that names the action, the scope, and the bypass behavior with zero filler. Every clause earns its place.

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 zero-parameter tool with an output schema present, the description need not explain return values, and it sufficiently conveys scope and effect. The only shortfall is the absence of auth/permission and synchronous-vs-async behavior for what is clearly an expensive forced refresh.

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 takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. The description adds no parameter context because none is needed.

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 states a specific verb ('Force an immediate re-crawl') and an exact resource scope ('all configured subtrees'), and the phrase 'bypassing TTL and version checks' distinguishes it from the read-only siblings (list_pages, search_pages, get_page). An agent can tell this is a cache-invalidation operation without opening any schema.

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 rather than stated: 'bypassing TTL and version checks' suggests this is for forcing freshness when cached data is unacceptable. However, there is no explicit when-to-use, when-not-to-use, or named alternative, so the agent must infer the trigger condition itself.

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