swg_gate

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

The only annotation is readOnlyHint=false, which carries almost no actionable information, so the description bears the full burden and delivers: it enumerates the distinct deny causes (stale version, reclaimed grant, peer preemption, unconfirmed comparand), states that version alone cannot detect a reclaim, and lists out-of-guarantee scenarios (multi-host, network mounts, divergent history, semantic correctness, auto-merge).

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?

Front-loads the core purpose and the 'call it immediately before' instruction, and every clause carries decision-relevant content. It is dense and somewhat run-on, particularly the long parenthetical listing deny reasons, but nothing is padding.

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?

No output schema exists, yet the description documents the return contract (decision=proceed, or DENIES with reason=stale_view), the failure-recovery path, and the tool's guarantee boundaries. An agent has everything needed to call it, interpret the result, and act correctly.

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 does so for the two non-obvious integers — both comparands must come from the earlier swg_read, and expected_generation is identified as the owner_generation — which is meaning the schema cannot convey. It does not explain `path`, though that parameter is largely self-evident.

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 precise verb+resource+scope: verify a file is STILL unchanged and under the same grant, using both comparands. An agent can distinguish it from siblings like swg_read (initial read) and swg_reacquire (recovery after deny) without opening any schema.

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?

Explicit when: 'Call this immediately BEFORE any irreversible external action you decided from that read', with concrete examples (webhook, PR, deploy, message). Explicit what-to-do-on-failure: 'do NOT take the action — swg_reacquire, re-read, re-decide', naming the alternative sibling.

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