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

Annotations already flag this as a non-read-only, non-idempotent, open-world operation; the description adds that some failures are not retryable by the tool at all and need in-app account reconnection. That is genuine behavioral context beyond the annotations. It stops short of warning about duplicate attempts or what happens to the publication after a retry is queued.

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?

One front-loaded sentence with a useful parenthetical caveat; nothing is wasted. Slightly awkward phrasing but appropriately sized for a one-parameter mutation.

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 single-parameter mutation with no output schema, the description covers the failure context and the precondition check well, but leaves the parameter unidentified and does not say what a successful retry produces (new attempt, rescheduled post, immediate republish). Adequate but with clear gaps.

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% and the single parameter publication_id is never explained — where to obtain it, whether it is the same ID surfaced by get_video, or what format it takes. The parenthetical points at get_video for error text but says nothing about the ID itself, so the description does not compensate for the undocumented parameter.

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 states a specific verb ('tries again') and resource ('a post that failed'), narrowing the action to network-failed publications. It does not explicitly distinguish retry_publication from the sibling retry_video, but 'post' vs. video contextually separates them. Clear enough for an agent to select it.

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 gives real gating guidance: read the error first via get_video, and do not retry when the error requires the user to reconnect the account in the app. That is a when-to-use and when-not-to-use rule. It lacks an explicit cross-reference to retry_video or cancel_publication as alternatives.

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