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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description adds real value with partial-update semantics (omitted fields stay as they are) and the published-post restriction, but it never explains why the tool is flagged destructive — e.g. whether supplying channels replaces per-channel text/settings wholesale — which is exactly the risk an agent needs to know before calling it.

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 short sentences, each doing distinct work: what can change, merge semantics, and the hard exclusion. Front-loaded and free of 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 mutation tool with 5 parameters, low schema coverage and no output schema, the definition covers the conceptual model (partial update, draft-only) but leaves the two most complex inputs — the `when` format and the nested channel-override object — undocumented anywhere, and says nothing about what is returned or how validation failures surface.

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?

With only 20% schema description coverage (only id is documented), the description does compensate partially by naming the four editable field groups. It adds nothing about the `when` string format (ISO 8601? timezone?) or about the channels array accepting either plain ids or per-channel override objects with nested text/title/mediaIds/settings, so the highest-risk parameter remains unexplained.

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 (change) and resource (draft or scheduled post) plus the editable fields (text, channels, media, time), which clearly separates it from create_post and delete_post. It does not distinguish itself from reschedule_post, whose name suggests overlapping time-change behavior, leaving some ambiguity about which tool owns a time-only edit.

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?

Provides a genuine when-not rule — published posts cannot be edited — which correctly scopes usage to drafts and scheduled posts. However, it names no alternative for the obvious overlapping case (rescheduling via reschedule_post) and gives no prerequisites about permissions or post ownership.

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