Act on many accounts

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

Annotations supply only destructiveHint=true, so the description carries the real behavioral burden and does: delete removes accounts plus all their projects and files forever, suspend signs them out immediately and blocks app, keys and MCP, and self/last-admin targets are skipped with a reason. It even discloses the return envelope (action, changed, unchanged, skipped[], nextCursor) so the caller knows what partial-success looks like.

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 critical precondition ('Admins only') is front-loaded, and the remaining clauses are packed with distinct facts: destructiveness, suspend side effects, skip rules, batch cap, pagination, return shape. No sentence repeats the name, title, or schema verbatim.

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 5-parameter, nested-filter, destructive bulk tool with no output schema, the description covers permissions, action semantics, safety skips, batching limits, pagination, and the response shape. Nothing an agent needs in order to invoke it safely and correctly is missing.

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 100%, so the baseline is 3; the description adds operational meaning on top by explaining the ids-vs-filter precedence and the cursor re-call loop with the same filter. It does not add syntax detail for q, flagged or verified beyond what the schema already documents, which keeps it below a 5.

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 opens with a specific verb set (approve, suspend, reinstate, delete) against a specific resource (many accounts) and states the two targeting modes (explicit ids or every match of filter, 'as list_users'). An agent can distinguish this bulk mutator from the read-only list_users sibling without opening either 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?

It gives clear selection guidance: use ids, or omit them to act on a filter; it caps the batch at 50 and instructs to re-call with nextCursor until null. It also states the admin-only precondition and the self/last-admin skip behavior. It stops short of naming when an agent should prefer a different tool over this one, so it is strong context rather than explicit when-not guidance.

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