neurover_cleanup_start

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the mutation risk is structured data. The description adds genuinely new behavioral facts: the work is asynchronous ('в фоне'), chunked ('порциями') and restart-resilient ('переживает перезапуск') — but says nothing about what happens to already-deleted files, whether the call is idempotent, or what handle it returns for tracking.

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 with the action front-loaded and the behavioral caveats trailing. Nothing is padded or repeated from the annotations.

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, asynchronous, no-output-schema tool the description covers the essential async/resumable traits, but leaves the monitoring path (cleanup_status), failure behavior and the origin of jobId undocumented. The Russian-only text may also mismatch the language of the surrounding toolset.

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?

Only one parameter, jobId, with 0% schema description coverage — the schema gives just a uuid format. The description implies the id refers to an approved cleanup job but doesn't say where to obtain it (cleanup_scan/approve) or whether a stale id is rejected.

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: 'запустить одобренное удаление' (start the approved deletion) as step 5 of cleanup. The sequencing marker and the word 'одобренное' separate it from cleanup_scan, cleanup_approve and cleanup_step, though it never names those siblings 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?

'Шаг 5' and 'одобренное удаление' imply a prerequisite (approval must already have happened), which is real ordering guidance. However, it never says what to do instead if the job isn't approved, nor points to cleanup_status for monitoring or cleanup_pause/cancel once running.

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