Edit a draft or scheduled post

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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, but the description adds real context beyond them: partial-update semantics ('omitted fields stay as they are'), cross-channel rule validation, the constraint that a scheduled post must remain publishable, and the immutability of channel targeting after creation. It stops short of describing failure modes or response shape, so it is strong but not exhaustive.

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 tight sentences, no filler, and the editability scope is front-loaded before the eligibility restrictions and alternative tool. Each sentence carries distinct information (what changes, partial semantics, validation, restrictions).

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 5-parameter mutation tool with nested settings, no output schema, and no enum parameters, the description supplies the needed eligibility rules, validation behavior, and channel-fixity constraint. Minor gaps remain around error/failure behavior and concurrency, but nothing essential for correct invocation is missing.

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 60% schema description coverage, the schema documents settings, scheduledAt, and mediaAssetIds, but the description adds a key constraint the schema does not express: settings may contain only ONE channel's settings, selected via settings.__type, and scheduledAt is meaningful only for scheduled posts. postId remains undocumented in both, though its meaning is obvious from context.

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 precise verb (change) plus the resource (draft or scheduled post) and enumerates exactly what is editable: caption, media, one channel's settings, scheduled time. It also explicitly distinguishes itself from the sibling create_post ('to post somewhere else, create a new post'), so an agent can route correctly without opening either 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?

Covers when to use it (draft/scheduled posts), when not to (published and failed posts cannot be edited), and the alternative tool when the goal is different channels (create_post). The 'omitted fields stay as they are' note further clarifies the invocation contract for callers.

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