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

No annotations are provided, so the description carries the full burden, and it does substantial work: it discloses the price ($0.001 USDC), the acquire/complete/release lifecycle, and a real failure mode ('An expired lease can hide a completed external effect; reconcile first'). It stops short of stating what happens on lock contention (fail vs. block), what acquire returns, or whether calls are idempotent, so it is not exhaustive for a no-annotation mutating tool.

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 core purpose and lifecycle are front-loaded and earn their place, but a large trailing block covers product-family routing ('unclear capability/provider → use free /api/discover...') and workflow-recipe boilerplate plus a list of things Agent Action Gate does not do, most of which is not specific to action_lock. The useful content is diluted by shared catalog copy.

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?

An output schema exists, so return values need not be described, and the description covers cost, lifecycle, concurrency rationale, and when to skip the tool. The main remaining gap is contention/error behavior on a failed acquire and how the lease_token flows between calls, which an agent must infer.

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 the baseline is 3, but the description adds genuine meaning beyond the schema by explaining the operation ordering (acquire before execution, complete after confirmed success, release after confirmed failure) and the lease-expiry hazard, which the schema's per-branch const operations do not convey. It still says nothing about lease_ttl_seconds vs. dedupe_ttl_seconds or payload_hash semantics.

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 ('Action Lock ... Prevent duplicate side effects across agent retries, crashes, and concurrent workers') and explicitly contrasts itself with the nearest sibling: 'Agent Action Gate asks whether an action should be performed; Action Lock asks whether it is already running or completed.' An agent can separate the two without opening either 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?

Gives explicit when-to-use ('If an action has side effects and may be retried or executed concurrently, acquire before execution'), lifecycle ordering (complete after confirmed success, release after confirmed failure), positive examples (payments, purchases, orders, emails, transactions, writes) and a when-not ('Avoid pure reads or equivalent provider-side idempotency'). It also names alternatives (Agent Action Gate, /api/discover, route_tool) with the conditions that select them.

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