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

Annotations already flag destructiveHint=true and readOnlyHint=false, yet the description still adds irreversibility ('cannot be undone'), the exact data lost (likes and comments), the fact the post survives on the calendar and can be republished, and the platform-level refusal paths. It also explains what the answer looks like when deletion is not permitted, which no annotation conveys.

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?

Front-loaded with the destructive action and its consequence, then scoping, then platform caveats, then consent, then the alternative — a sensible ordering. The single paragraph is dense and long, but each clause carries distinct routing or safety information, so little is wasted.

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, no-output-schema tool this covers everything an agent needs: consequences, consent requirement, account scoping, platform refusals, and post-deletion state. No return-value explanation is required since the response shape is described behaviorally ('the answer says so plainly').

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 100%, so the baseline is 3; the description earns above that by explaining the connection_id optionality rule ('may be left out only when the post went out on one account') and pointing to get_post_performance for multi-account posts. post_id and brand_id are only referenced as coming from siblings, which the schema already states.

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 and resource (delete a post that already went out from the social account it was published on), plus the visible consequence (gone from public profile with likes and comments). It separates itself from the queued-post sibling by name, so an agent can route between them without opening schemas.

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?

Gives explicit when-not guidance ('To stop a post that has not gone out yet, use cancel_queued_post instead') and a hard precondition ('Only with the user's explicit go-ahead'). It also names platform exclusions (Instagram app, YouTube Studio for uploads-only channels) so the agent knows when the call will be refused.

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