line_retry_job

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

Adds behavior beyond the annotations: the state transition (failed to pending), that pickup happens on the next worker run, and the reply-token expiry caveat with push as fallback. Annotations already cover safety and idempotency, so this supplementary context is what earns credit.

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?

Two short sentences with zero filler; the core action is front-loaded and the failure caveat follows as qualification.

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 no output schema, the description covers the action, the timing of pickup, and the failure mode well. It could still note that jobId is sourced from line_failed_jobs or what a successful retry returns.

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 0% and the description never mentions jobId. With a single required parameter, a UUID pattern alone does not tell the agent where the value comes from (presumably line_failed_jobs), which is a real gap at this coverage level.

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 resource: putting a failed job back to pending for the next worker run. It is distinguishable from siblings like line_failed_jobs (inspect) and line_push_text (send), though it never names those siblings explicitly.

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 usable context: reply tokens expire soon after the event, so a job that replies may fail again, and push is the fallback. This effectively tells the agent when retry is the wrong choice, but it does not spell out prerequisites or an explicit 'do not use when' clause.

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