neurover_cleanup_verify

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, and the description's "deletes nothing" is consistent with that safety profile rather than contradicting it. It adds the background/asynchronous trait, but says nothing about cost (hashing reads file bytes, maxBytes bounding), what happens on a hash mismatch, or how results surface.

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?

Three short clauses, front-loaded with the step number and operation, with no filler. It is terse to the point of omitting needed detail, but nothing present is wasted.

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?

A five-parameter, nested-object tool with no output schema and 0% schema documentation needs more than this. An agent cannot tell what verification returns, how mismatches are reported, or how groupRetention interacts with the 'deletes nothing' promise before calling it.

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% across 5 parameters, so the description must carry the load — yet it only explains 'background'. The purpose of groupIds, maxBytes (a size cap), and especially the nested groupRetention map with keep_one/delete_all values is left entirely to inference; the latter also sits awkwardly beside the claim that nothing is deleted.

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 a specific operation (SHA-256 verification of originals in selected groups) and places it as step 3 of the duplicate-cleanup flow, which distinguishes it from siblings like neurover_cleanup_scan or neurover_cleanup_approve. It does not explicitly name the sibling it should be chained with, but the verb+resource is unambiguous.

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?

It marks the step as optional and notes background=true runs asynchronously without waiting, which implies when to use it. However, it never says when to skip it, what precondition (a prior scan/step-2 result) is required, or where to fetch the verification outcome — guidance that matters for a multi-step cleanup flow.

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