gc_notify

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

With no annotations provided, the description carries the full burden. It discloses durable mailbox creation and unread/read semantics, but does not say what happens on push after drain, how duplicates or re-delivery are handled, or any failure/error behavior. It's adequate but not rich.

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 and front-loaded with the purpose, then the actions, then the integration pattern. The use of bullets and the integration steps is well structured. It's slightly verbose in the trailing 'daemon guarantees' sentence which could be trimmed, but overall efficient.

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?

For a tool with no output schema and 7 params, this covers the core integration flow well. It explains the checkpoint-driven polling contract, which is the most important behavioral context. Missing details include return format and error handling, but for a mailbox abstraction the polling loop guidance is the critical piece and it's present.

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. However, the description adds two values: the 'drain' action's checkpoint semantics (since) and the 'harnesses decide how to surface drained events' guidance. It also contextualizes the push/drain/list actions against their parameters, adding meaning beyond the plain schema.

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 clearly states this is a 'notification mailbox for durable consumer polling' with the three actions (push/drain/list) explicitly enumerated. It distinguishes from siblings by describing a specialized durable mailbox with unread/read semantics, which no sibling name suggests.

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?

Provides an explicit 4-step recommended integration pattern (persist checkpoint, drain with since, handle events, advance checkpoint). This is strong alternative-usage guidance that tells the agent exactly when and how to invoke the drain action within a consumer loop.

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