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

Goes well beyond the annotations (destructiveHint, idempotentHint) by disclosing concrete effects: revocation blocks search, originals, Markdown, OKF and ZIP downloads even with an existing session or key, team access is re-evaluated per request from current membership, and responses use private, no-store caching. This is exactly the kind of blast-radius detail an agent needs before a destructive call.

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 purpose is correctly front-loaded, but several sentences ('Sharing a collection grants current and future files... Sharing does not publish a resource... The initial grant requires...') describe the sharing side rather than revocation and read as carryover from the sibling tool, diluting focus in a fairly long block.

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 mutation with no output schema, the description supplies the essential context: what gets cut off, that effects apply to live sessions and keys, that only the owner can change sharing, and cache behavior. No return-value info is needed absent an output schema, so the picture is nearly complete.

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?

There is a single required parameter (collection_id) with 100% schema description coverage, so the schema already documents it fully. The description adds no identifier format or lookup guidance beyond the schema, making the baseline 3 appropriate.

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 first sentence gives a specific verb ('Withdraw') and resource ('the team grant from your collection'), which unambiguously distinguishes it from the sibling share_collection_team (the inverse) and unshare_base_team (collection vs base). An agent can route correctly without opening the 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?

Usage is implied by the clear inverse relationship to share_collection_team, but the description never states when to reach for this tool versus alternatives, nor does it name a sibling. It adds adjacent rules (owner-only changes, org API keys stay within existing grants) that shape applicability but don't constitute explicit when/when-not guidance.

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