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

Annotations only say readOnlyHint=false, openWorldHint=true, and destructiveHint=false. The description adds the important context: retries reuse original inputs, a target that may already be live is excluded, each retry is a real new external attempt, and the user must confirm. That is the side-effect profile an agent needs before calling it, and it does not contradict the annotations.

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, and the scoping rule comes first, followed by the exclusion and the confirmation requirement. Every sentence carries a distinct constraint, and nothing is repeated from the title or schema.

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 one-parameter mutation with external side effects and no output schema, the preconditions, exclusions, and safety requirement are all covered. It stops short of saying what the call returns or whether a retried target can itself be retried later, which leaves small 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?

The schema already documents the single parameter at 100% coverage and points back to create_publication's return value. The description adds meaning it does not state outright: the id must refer to a finished publication that has failed targets, which narrows valid inputs beyond the uuid format alone.

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 and scope: re-run only the failed targets of a finished publication, using their original inputs. That clearly separates it from create_publication (new publication) and get_publication (read), so an agent can pick it without opening the 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?

Gives a clear precondition (the publication must be finished and have failed targets) and an explicit exclusion (outcome_unknown targets are never retried). It also tells the agent to confirm with the user first, but it never names a sibling alternative for the non-retryable case, so the routing guidance is not fully closed.

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