Retry Image Tasks

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

Despite annotations covering idempotency and destructiveness, the description adds substantial context: it will never re-bill unknown-result requests, never redraws (repairs from original responses while preserving corrupted files), and aborts the entire batch if any item is unsafe. This is exactly the operational safety nuance annotations cannot convey.

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?

Dense but efficient; the scope (1–20 items, safe stages only) is front-loaded, then each subsequent sentence adds a distinct operational rule. No filler, though the density borders on terse for a non-native reader.

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?

Output schema exists, so return values needn't be explained, and the safety/repair/cost logic is thoroughly covered. The only real gap is the unexplained meaning of checkpointer/thread_id/task_ids, which matters for correct invocation.

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% with 4 parameters and no descriptions. The description explains only repair_files (its repair-not-redraw semantics), leaving task_ids, thread_id, and checkpointer completely undocumented in both schema and prose.

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+resource (retry image tasks) with explicit scope: 1–20 items, safe stages only, idempotency-key preserved. It distinguishes itself from siblings like submit_image_tasks by emphasizing it does not re-issue billed requests, though it never names a sibling tool directly.

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?

Provides clear when-conditions: retry only when safe_to_retry holds, reuse successful/in-progress items, use repair_files=True for verification failures, and check cost first when a POST may have been sent without a checkpoint. Exclusions are stated (whole batch blocked by any unsafe item), though no sibling tools are named as alternatives.

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