pbs_gc_start

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

The description discloses mutation and high impact, dry-run behavior, permanent removal (no undo), and async return as UPID. Without annotations, this covers the key traits. It could mention required permissions or state prerequisites, but given the tool's nature, it is sufficiently transparent.

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 a single dense sentence with front-loaded 'MUTATION (HIGH)' for impact. Every phrase carries information without fluff, making it highly concise and well-structured.

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?

The description covers purpose, safe default, danger, execution trigger, output type, and progress-checking tools. For a focused mutation tool, this is nearly complete. It could mention permissions or prerequisites, but overall it provides sufficient context.

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 100%, so baseline is 3. The description adds value by explaining the confirm parameter's effect (dry-run vs execution) and the overall default behavior, which goes beyond the schema description.

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 'start', the resource 'garbage collection on a PBS datastore', and the default dry-run behavior. It distinguishes from sibling tools like pbs_gc_status by mentioning progress checking, making the purpose specific and unambiguous.

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 explains the dry-run default and that confirm=True executes the GC, providing clear usage guidance. It warns about permanent removal (no undo), but does not explicitly list when to avoid using the tool, though the caution is implicit.

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