refresh_catalog

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

Annotations already declare destructive=true, idempotent=false, and openWorldHint=true, so the description earns credit for what it adds: the replacement is *atomic* (all-or-nothing, no partial snapshot) and the incoming metadata is *validated* before swapping. It still doesn't say what happens when validation fails or whether the prior snapshot survives a failure.

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 sentence with no filler, front-loading the fetch step before the mutation. Every clause (upstream, atomically, validated, offline) carries distinct meaning.

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?

An output schema exists and annotations cover the safety profile, so much of the burden is lifted. However, for a destructive, network-dependent operation, the description omits failure behavior (validation rejection, upstream unavailable) and whether the old snapshot is recoverable — clear gaps even if the agent can still invoke it correctly.

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 single parameter is fully documented in the schema (coverage 100%), including the plan-versus-execute semantics of confirm. The description adds nothing about confirm, so baseline 3 applies — the schema is doing all the parameter work.

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?

Names a concrete two-step action (fetch upstream metadata, then replace the offline snapshot), which is far more specific than the tool name alone. It implicitly distinguishes itself from read-only siblings like verify_catalog or check_update, but never names an alternative explicitly.

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 explains what happens but not when to call it: no mention of when a refresh is needed versus verify_catalog, check_update, or list_updates, and no prerequisites such as network availability. The only usage signal comes from the structured fields (openWorldHint, destructiveHint), not the prose.

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