refresh_import_metadata

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the write-plus-external-server profile is known. The description adds genuinely new context beyond that: the mutation is scoped to 'only its indexed Jellyfin item' (blast-radius limit) and that it reports pending/mismatched state rather than forcing convergence. It still omits idempotency, failure modes, and whether a mismatched/conflicting revision aborts the call.

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?

Two sentences, front-loaded with the action, no filler. Density of domain jargon ('owned-import metadata revision', 'indexed Jellyfin item') costs some readability but every clause carries 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?

This is an open-world mutation with three undocumented required parameters and no output schema, which raises the description's burden. It partially compensates by describing the scoped target and that the result reports pending/mismatched state, but leaves the shape of that report and the semantics of the revision token unexplained, so an agent cannot reliably construct a correct call.

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 description coverage is 0% for all three required parameters, so the description must carry the burden and largely does not. 'Current ... revision' vaguely hints that expectedRevision is a concurrency/optimistic-lock token, but jobId vs profileId are never explained, nor is the meaning of the 'initial' sentinel in the expectedRevision pattern.

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 specific verb (reapply/refresh) paired with a specific resource (the current owned-import metadata revision and its indexed Jellyfin item), so the action is identifiable. However, it never names or contrasts with the closest siblings — update_import_metadata, restore_import_metadata, inspect_import_metadata — leaving the agent to infer the boundary between 'reapply current revision' and 'update' or 'restore'.

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 only implied: 'reapply the current' and 'reports pending or mismatched state' suggest it is for repairing drift rather than making changes, but the description never states when to pick this over update_import_metadata or restore_import_metadata, nor any preconditions (e.g. that the revision must already be owned/applied).

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