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

Annotations only say readOnlyHint=false, so the description carries most of the burden and does add real value: it discloses that only FAILED items are eligible, that the action is confirm-gated with a preview-only default, and that it will not double-send on its own. What it does not disclose is what the retry actually produces (re-sent message? recomputed schedule?) or whether the FAILED state is consumed afterward.

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 with the action and eligibility front-loaded, plus a safety note. The parenthetical "confirm-gated: previews until confirm: true" largely duplicates the schema's own `confirm` description, which is the only mildly wasteful element.

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 two-parameter mutation with no output schema, the description covers eligibility, safety, and the confirm gate, which is most of what an agent needs. It is slightly thin on post-success behavior and on what happens if the target item is not in FAILED state.

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 50%: `confirm` is documented in the schema and the description only restates that gating, while `id` has no description in either place. The description implies `id` identifies the failed program item, but it never says whether that is an occurrence id or a program-item id, leaving the one undocumented parameter under-specified.

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?

"Run one FAILED program item again now" gives a specific verb (re-run), a narrow resource (a single program occurrence), and a qualifying constraint (must be FAILED). An agent can distinguish this from list_program_occurrences or get_program without opening any 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?

The description makes the trigger condition clear: use it on an item that has already failed, right now. It also removes the main hesitation an agent might have ("will something else retry this?") by stating nothing is retried automatically. It stops short of naming an alternative or stating when NOT to use it, so it is not a full when/when-not treatment.

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