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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds genuinely non-obvious behavior: the attachment is detached rather than permanently purged, storage cleanup is delayed, and existing client approval is invalidated requiring a fresh review. That is exactly the consequential side-effect information an agent needs before calling a destructive tool.

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?

Four short sentences, front-loaded with the action and the most surprising behavior (delayed cleanup), then consequences, then a safety caveat. Slight redundancy: the final 'Never supply a personal media ID' repeats a constraint already present in every schema property description.

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 3-parameter destructive mutation with no output schema, the description covers the important ground: what is actually removed, that cleanup lags, and that approval state is affected. It does not say what the call returns or whether the post must be a draft at call time, which are the remaining 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 description coverage is 100% and every parameter already documents 'Exact ID returned by a Company tool; never a personal platformId'. The description's 'Never supply a personal media ID' reinforces the same rule but adds no new meaning about workspaceId, postGroupId, or mediaFileId, 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 ('Detach') and a precisely scoped resource ('a selected attachment from an Agency draft'), which is more accurate than the tool name's 'delete'. The 'personal media ID' caveat implicitly separates it from the personal-account delete_media / prune_media_reference siblings, so an agent can route 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?

Clear operating context: this is for Agency drafts, and after changing media the agent must request a new review since approval is invalidated. It gives a hard constraint ('Never supply a personal media ID') but never explicitly names the alternative tool (delete_media, prune_media_reference, company_list_post_media) or the condition that selects it, leaving that to inference.

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