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

Annotations already flag destructive=true and idempotent=true, but the description adds non-derivable behavior: the default dry-run/listing mode, the bulk scope across all flows, and the owner/admin permission requirement. These are exactly the contextual facts an agent needs before invoking a destructive bulk operation.

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 sentences ordered by importance: destructive scope first, then the safety/preview behavior, then the inspection alternative, then the permission gate. No filler, no repetition of the title.

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 two-mode operation with no output schema, the description covers scope, preview behavior, alternative tool, and auth. It does not say whether the removal is reversible or what the preview/list response looks like, which is a minor residual gap given idempotentHint is provided.

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% and both parameters (org_id, confirm) are fully documented in the schema, including the same preview semantics the description restates. The description adds no syntax, format, or meaning beyond the schema, so the baseline 3 applies.

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 (Remove), a precise target population (every person who is not a member of the organization or whose email domain is not allowed), and the blast radius (from all organization flows). This clearly separates it from the singular remove_collaborator/remove_member siblings without the agent needing to open a 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?

Explicitly describes the two modes ('Without confirm true it only lists who would be removed'), names an alternative tool for inspection ('Use get_org_security to see them first'), and states the authorization prerequisite ('Only an owner or an admin'). When-to-use, safe-preflight, and who-can-call are all covered.

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