gc_sync

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

No annotations are provided, so the description carries the full burden. While it lists actions and their basic intents, it doesn't disclose whether classify/dismiss are destructive (reversible or not), whether run triggers persistent side-effects, or whether specific permissions/auth are needed. The description hints at behavior through action names but leaves mutation semantics underspecified.

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—a one-line purpose plus a terse action list with inline parentheticals. The format is scannable and front-loads the core purpose. A bit telegraphic, but appropriately sized for a dispatcher-style tool with many sub-actions.

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 6 actions and a nested object param (resolution) with no output schema, the description reasonably maps each action to its input parameters. However, it doesn't explain what the classify resolution object should contain, what status/rules return, or how results are structured—gaps that matter for a multi-action tool without an output schema.

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 parameters are already documented. The description adds value by tying specific parameters to actions (id for classify/dismiss, reason for dismiss, resolution for classify, rule_file for run/rules), which helps the agent know which params apply to which sub-operation—beyond what the flat schema alone conveys.

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 identifies this as a 'Reconciliation engine for data hygiene' and enumerates six distinct actions with parenthetical clarifiers (status = last runs/pending reviews, run = trigger sync, etc.), which maps actions to behaviors. It doesn't explicitly distinguish from siblings like gc_recall, gc_retain, or gc_reflect, though the reconciliation-for-hygiene framing provides some differentiation context.

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 action list implicitly conveys when to use each sub-operation, but there's no explicit guidance on when to choose this tool versus sibling reconciliation/retention tools like gc_recall or gc_retain. No exclusions or alternative recommendations are given, leaving cross-tool selection to inference.

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