pbs_verify_start

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

With no annotations provided, the description carries full responsibility. It discloses that the tool is a mutation, defaults to a non-destructive dry-run (read-only check) but is heavy I/O, and is asynchronous returning a UPID. This provides essential behavioral context. However, it could further mention whether the verification creates a task or has specific permission requirements.

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 brief (two sentences) and front-loads the core purpose with 'MUTATION: start an integrity verification run'. It efficiently conveys key behavioral traits. Minor improvement could be structuring the confirm and async details more clearly, but overall it is well-organized and concise.

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 the essential behavior (start verification, dry-run, confirm to execute, async) and notes the output type (UPID). Given that an output schema exists, the return format is partially documented. However, it lacks details on required parameters (e.g., 'store'), fails to describe the verification scope, and does not specify permissions or side effects beyond I/O. For a mutation tool with 6 parameters, it leaves gaps.

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 only 17% (only proximo_target has a description). The tool description does not compensate: it only mentions 'confirm' and hints at its boolean nature, but does not explain other parameters like 'store' (required), 'ns', 'backup_id', 'backup_type'. The agent would need to infer from names or schema defaults, which is insufficient.

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 identifies the tool as starting an integrity verification run on a PBS datastore, using specific verb+resource. The 'MUTATION' prefix and mention of 'dry-run' distinguish it from read-only tools and siblings like pbs_gc_start (garbage collection) or pbs_prune (pruning). The tool's unique purpose is 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 default dry-run behavior and how to execute with confirm=True, and notes heavy I/O. However, it does not explicitly state when to use this tool versus alternatives (e.g., pbs_gc_start for garbage collection, pbs_prune for pruning). The guidance is sufficient for basic usage but lacks comparative context.

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