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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally. The description genuinely adds behavioral context the annotations do not: the pre-scheduling precondition and the rejection condition once publishing/published. It doesn't say what happens if no editable field is supplied or what a partial-failure/validation response looks like, so the addition is useful but not rich.

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 sentences, front-loaded with the action and its editable facets, then the timing constraint. Parameter names are quoted inline, which edges toward restating the schema, but the constraint sentence earns its space. No 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 six-parameter mutation with an output schema and rich annotations, the description covers the critical preconditions an agent needs before invoking. Remaining gaps are minor: no-op behavior when only post_id is passed, and no note on whether edits to target accounts invalidate existing schedule entries.

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 83%, so the baseline is 3. The description goes beyond the schema by explaining where remove_media_ids values come from (media_id listed by the schedule preview) and by framing target_account_ids as a replacement set, which is semantic guidance not stated in the schema text.

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 (edit) plus resource (post) and then enumerates exactly which facets are editable: body, target accounts, attachments by media_id, and quote via quote_url/remove_quote. This maps the full edit surface in the first sentence and is trivially distinguishable from delete_post, cancel_post, or create_post.

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: attachments and quotes can change only before the chain is scheduled, and the call is rejected once the post is publishing or published. It also points at preview_schedule as the source for media_ids. It stops short of naming an alternative tool for edits that are no longer allowed (e.g., cancel/recreate), which keeps it from a 5.

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