start_batch

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

Beyond annotations, it discloses important behavior: background execution, immediate job_id return, required polling via job_status, per-file failure isolation, and a JSON report written to output_dir. It does not clarify overwrite/skip_existing behavior or permission requirements, but it adds substantial operational context.

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 compact and front-loads the core async batch behavior before covering normalize, match_reference, failure handling, and reporting. The semicolon-heavy style is dense but every clause carries relevant information.

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 15-parameter batch-processing tool with 0% schema description coverage and no output schema, the description is too thin. It adequately explains async execution and failure reporting, but most parameters and their effects on the batch pipeline are left unspecified.

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% across 15 parameters, so the schema provides almost no semantic help. The description explains only normalize, match_reference, and output_dir reporting; it leaves steps, preset, format, naming, dry_run, quality, metadata, overwrite, recursive, project_id, skip_existing, and inputs largely undocumented.

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 operation: batch-processing files/folders/globs through one pipeline in the background. It clearly frames the tool as asynchronous batch processing, though it does not explicitly contrast itself with siblings like apply_to_file or run_tool.

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 context: the call returns a job_id immediately and the agent should poll job_status. This effectively tells the agent how to use the tool after invocation, but it does not explicitly say when to prefer it over single-file or synchronous alternatives.

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