prune_failed_subjects

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

No annotations are provided, so the description carries the full burden. It discloses that the tool deletes files (destructive), reads a QC file, and supports dry-run preview. It also specifies the scope (only cortical_tiles outputs) and the deletion condition. It could be more explicit about side effects or reversibility, but the information is sufficient for safe invocation.

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 three concise sentences: purpose, detailed behavior, and usage tip. It front-loads the verb-resource pair and avoids fluff. Every sentence adds essential information without redundancy.

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?

Given the existence of an output schema, the description does not need to explain return values. It covers the input format, behavior, and a safety preview. Missing context includes dependencies (e.g., QC file must exist) and scope confirmation (ensures it only deletes cortical_tiles outputs), but overall it adequately prepares an agent 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?

The schema coverage is 0%, so the description must compensate. It explains the 'qc' parameter (TSV/CSV with specific columns) and 'dry_run' (preview mode), but 'output' is not explicitly defined—only implied as the cortical_tiles output directory. This adds some value but leaves a gap for one required parameter.

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 clearly states the verb (remove), resource (cortical_tiles outputs), and condition (subjects that failed QC). It explains how failure is determined (qc==0 or absent from QC file), making the tool's purpose precise and distinct from siblings like purge_subject.

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 provides context for when to use this tool: after cortical_tiles if the QC flag was not used initially, and it offers a preview option (dry_run=True). It does not explicitly list alternatives or when not to use it, but the equivalence to a flag and the sample use case are clear enough for an agent to infer appropriate usage.

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