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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is mostly covered. The description adds genuinely new behavior: partial-update semantics ('set only what was asked'), caption replacement semantics, refusal for non-draft posts, and the guarantee that the draft 'stays a draft and is never posted automatically'. It does not cover failure modes or what happens on conflicting parameters such as scheduled_at plus clear_time.

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?

It is front-loaded with the usage trigger and organized into trigger, parameter guidance, exclusions, and guarantees. It is long, and the TikTok post-screen list reads as a run-on enumeration, but nearly every clause carries operative information rather than 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 15-parameter destructive mutation with an output schema and annotations already present, the definition supplies the routing conditions, per-platform value sets, dependency tools, and the no-auto-post guarantee. There is no material gap that would cause an agent to call it incorrectly.

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 0%, so the description must carry the burden and it does: post_id's source, caption replacement plus the YouTube title-in-first-line rule, scheduled_at's ISO 8601-with-offset format, clear_time, account_id's source tool, per-platform privacy values, disclose's relationship to brand_organic/brand_content, aigc, and mode direct/inbox. Nearly every one of the 15 parameters gets meaning beyond its name.

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 opens with a concrete verb and resource ('change a post that is still a draft') and gives concrete example utterances ('make the caption shorter', 'turn comments on'). It tells the agent exactly which object class this mutates, which clearly separates it from draft_post, plan_posts and delete_draft.

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?

It states both when to use it and explicit exclusions: scheduled or posted posts are 'refused', new drafts go to draft_post/plan_posts, removal goes to delete_draft. It also states the dependency on get_post_stats with status 'draft' for obtaining post_id, which is the routing condition an agent needs.

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