Retry failed work

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

With no annotations, the description carries the full behavioral burden and does so well. It discloses admin-only access, per-item transactions so live-job caps still apply, the 50-item cap, the response shape, the admin event write, and that non-admins are refused.

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?

The description is front-loaded with the admin-only constraint and action, then quickly covers lifecycle behavior, caps, return shape, event logging, and refusal behavior. Every sentence contributes useful context without waste.

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?

Although there is no output schema, the description supplies the return object shape. Combined with full schema parameter coverage and explicit auth, lifecycle, transaction, cap, and event behavior, it is complete enough for an agent to call this mutation tool correctly.

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 description coverage is 100%, so the input schema already documents q, ids, limit, since, and stage. The description reinforces the overall filtering model and cap but does not add parameter-level meaning beyond what the schema provides.

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 and resource: retrying matching failed projects and clips. It distinguishes itself from sibling lifecycle operations by saying it goes through the same lifecycle as retry_project / rerender_clip and is never a raw queue poke.

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 clear usage constraints: admins only, hosted non-admins are refused, and each call is capped at 50 items. It also ties its q/stage/since filters to list_failures, but it does not explicitly state when to choose this bulk retry tool over the single-item retry_project or rerender_clip alternatives.

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