sync_review

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

No annotations are provided, so the description carries the full behavioral burden. It describes the classification concept (guard-clean vs secret-guard flagged) but never states whether the call mutates state, whether review results persist, whether it requires specific permissions, or whether it is idempotent/safe to re-run. For a tool whose name suggests state reconciliation, these gaps matter.

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?

A single dense sentence with the core operation front-loaded and the workflow guidance trailing. No filler, though the all-caps bucket names and jargon make it slightly harder to parse at a glance.

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?

There is no output schema, so the description usefully sketches what the tool yields (two classified buckets) and how the result feeds `share`. With a single well-documented parameter, the main remaining gap is the undisclosed state/persistence behavior, which is a transparency issue more than a completeness one.

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?

Only one parameter, and schema description coverage is 100% — the schema already says `initiative` is the team initiative to review. The description's framing ('still-local nodes for') mirrors rather than extends the schema text, so baseline 3 applies.

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?

States a specific verb+resource (batch sync-review of a team initiative's still-local nodes) and describes the concrete output split (PROPOSE SHARE vs KEEP LOCAL). It also distinguishes itself from the sibling `share`, which is named as the follow-up action rather than a duplicate. It stops short of a clean 'use this instead of X' framing, but the operation 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?

Gives clear context: 'Review once, then `share` the approved ones — low-friction periodic sharing instead of deciding per capture.' This tells the agent this is a periodic batch triage step feeding `share`, contrasted with per-capture decisions. No explicit exclusions or prerequisites (e.g., when not to run it) are stated.

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