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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered. The description adds genuinely useful scope context by clarifying that the effect is 'ending their membership in that collection' — i.e. the accounts themselves are not deleted — which is not derivable from the annotations.

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?

Two sentences, both earning their place: the first front-loads the action and scope, the second provides a concrete follow-up. No redundancy or filler.

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 2-parameter mutation with no output schema, the description covers purpose, effect and a verification path. It omits failure semantics (e.g. partial removal when some IDs are invalid), whether an emptied collection persists, and any permission requirement, leaving minor gaps.

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 coverage is only 50% (collection_id has no schema description), so the description must compensate. It names both parameters and assigns each a role — account_ids as the accounts to remove, collection_id as the target collection — and 'one or more' conveys the minItems=1 constraint, closing most of the gap.

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 gives a precise verb ('Remove') plus resource ('accounts') and names both key identifiers (account_ids, collection_id), which distinguishes it from remove_videos_from_collection by the noun alone. It stops short of explicitly routing the agent against siblings like add_accounts_to_collection.

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 operation itself, and the description adds a post-action verification hint ('Use get_collection_accounts to check what remains'). It offers no when-to-use vs. when-not-to-use guidance, no prerequisites (permissions, ownership), and does not name alternatives for reversing the removal.

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