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

Annotations declare destructive/idempotent/openWorld, and the description adds genuinely new behavioral context: publication requires captured affirmative authorization, dryRun creates no publication and sends nothing, stale expectedRevision rejects the call, idempotencyKey should be reused on retry, and indeterminate outcomes are not treated as delivered. This goes well beyond what the annotations and schema convey.

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 when-to-use clause followed by prerequisites, then per-parameter notes and failure semantics. Dense and largely waste-free, though the telegraphic phrasing and repetition of confirmation/dryRun rules that also appear in the schema costs a little efficiency.

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, open-world mutation with 7 params and an output schema, it covers the approval workflow, preflight, staleness, retry and the ambiguous-outcome rule, so return values need not be explained. It stops short of stating rate limits, permission requirements, or what a successful publication job looks like downstream (e.g., how it relates to list_publications/cancel_publication).

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 71% and documents most parameters, so baseline is 3; the description adds real meaning on top by explaining that confirmationText must be a verbatim quote of the user's authorization (no magic phrase/language), that expectedRevision guards against stale content, and that idempotencyKey is for retry reuse. It does not add syntax detail for draftId or the channelId title-matching rule beyond the schema.

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+resource+effect: publishing a reviewed draft to a connected channel/group. It implicitly separates itself from schedule_post ('never bypass it with scheduling'), preview_post and list_channels (named as prerequisites), so the agent can distinguish it from the surrounding publication tools without opening their 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-to-use (reviewed draft, explicit user approval), names the prerequisite tools to call first (list_channels, preview_post), describes the dryRun alternative path, and states exclusions (do not bypass consent via scheduling; pending/uncertain is not delivered). Nothing about selection is left to inference.

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