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

Annotations only say destructiveHint=true and idempotentHint=false; the description goes much further by naming exactly what is affected (files), the recoverability of each mode (trash and quarantine are both restorable), and the guarantee that one copy per group (keep field) always survives. It also explains the 409/400 failure semantics, which the annotations cannot express.

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 destructive warning is front-loaded in the first clause, then parameters, guarantees, and error codes follow in a compact, scannable sequence. No filler sentences; every clause carries operational 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 destructive three-parameter mutation tool with no annotations beyond hints and no output schema, the description covers prerequisites, side effects, recoverability, and error handling well. It does not describe what the call returns (e.g., counts of trashed/quarantined files), which matters since no output schema exists.

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?

With 0% schema description coverage the description must carry the load: it defines both enum values of `action` precisely (provider trash vs. _dedup_quarantine folder, both recoverable) and constrains `group_ids` to the groups_* output of get_dedup_scan. `scan_id` is only implied via the 409 "scan not finished" note, so it is not fully documented.

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?

States a specific verb and resource ("Применить чистку к группам дублей") and immediately flags the destructive outcome in caps ("УДАЛЯЕТ ФАЙЛЫ"). An agent can distinguish it from delete_file (single file) and get_dedup_scan (read-only scan) 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?

Gives a hard precondition (group_ids must come strictly from the groups_* part of a get_dedup_scan result) and routes away from unavailable behaviour ("Безвозвратное delete через MCP недоступно"), plus 409/400 error conditions that tell the agent when not to call. It never explicitly names a sibling alternative such as delete_file, so it falls short of a full when/when-not/alternatives statement.

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