pbs_run_gc

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

Beyond annotations (destructiveHint: true), the description adds valuable behavioral context: GC traverses every chunk, frees unreferenced ones, runs async, returns a UPID immediately, and requires specific environment/permission flags. This exceeds what annotations alone convey and includes no contradictions.

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 short sentences, front-loaded with the primary action, and every word earns its place. No redundancy or filler.

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 key operational aspects: destructive effect, async execution, UPID return, and required confirm/auth flags. It does not explain the datastore or reason parameters, but an output schema exists and return value behavior is already summarized. Overall, it is sufficiently complete for a destructive background operation.

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%, so the description must compensate. It only explains the confirm requirement; reason and datastore are left completely unexplained. The agent has no guidance on what values are appropriate or what datastore scoping means.

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 opens with a specific verb and resource: 'Trigger a garbage-collection run.' It then explains exactly what GC does ('walks every chunk and frees those no longer referenced by any snapshot'), clearly distinguishing it from siblings like pbs_gc_status and pbs_prune.

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 tells the agent when to use it (to trigger GC) and provides important operational context: async behavior, immediate UPID return, and the need for PBS_ALLOW_WRITE=true and confirm=true. It does not explicitly name when-not-to-use or alternatives, but the GC-specific wording makes the use case clear.

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