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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered by structured data. The description does add useful behavior beyond that – the full set of terminal status values and the explicit 404-not-found case – but does not discuss freshness of progress data while a scan is running (running/executing states imply staleness), which is the key behavioral question for a polling tool.

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 dense sentence that is front-loaded with the resource and status, then layers in the group semantics and the error case. No filler, though the nested parentheses around group names make the middle clause harder to parse than necessary.

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?

With no output schema, the description bears the burden of describing the response, and it does so well – status enum, progress, both group categories, the `id`/`keep` fields per group, and reclaim_bytes. The only material gap is how scan_id should be obtained, which matters for a required parameter.

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?

There is one parameter, scan_id, at 0% schema description coverage. The description does not explain where scan_id comes from (start_dedup_scan return value or list_dedup_scans), though the 404 note implicitly confirms it identifies a scan. Some compensation, but not enough to offset the 0% coverage.

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 names the specific resource (dedup scan details) and enumerates what is returned – status values, progress, groups, reclaim_bytes – so the agent knows exactly what this call yields. It does not explicitly contrast with the sibling list_dedup_scans, which is the natural companion for discovering scan_id, so it stops short of full sibling differentiation.

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: the agent can infer this is the detail view for a known scan_id, and the mention that groups_same_folder entries carry `id` for execute_dedup gives a downstream path. However, there is no explicit 'call list_dedup_scans first to obtain scan_id' or exclusion guidance against the list tool.

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