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 does well: it discloses that the call blocks until the sync finishes, that it may take a long time on a large pending delta, and that it reuses the startup sync path. It omits any concurrency concern (e.g. what happens if a sync is already running) and any indication of what the call returns.

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 action and its trigger are front-loaded in the first sentence, with blocking behavior last. It is slightly longer than needed — the em-dash aside about backfill/recheck could be tightened — but every sentence carries real information.

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 parameterless, annotation-free maintenance call with no output schema, the description covers the essential agent-facing facts: what it does, when to invoke it, and that it blocks. It does not say what happens on failure or whether the call is idempotent, which are minor gaps for a zero-arg tool.

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, which is the baseline-4 case; there is nothing in the schema for the description to clarify or compensate for.

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 gives a specific verb and resource — "Manually trigger a SQLite cache sync against the archive" — and frames it as the manual counterpart to the sync the server runs at startup. This is the only maintenance action among the query_* siblings, so an agent can distinguish it without opening a 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?

It states the triggering conditions precisely: use when a sync, backfill, or recheck has just run and results may be stale. It does not explicitly say when to avoid calling it (e.g. during normal operation, or that query tools are the alternative), so it stops short of full when/when-not/alternatives guidance.

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