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

Annotations flag a non-read-only, non-idempotent, non-destructive, open-world call. The description adds material beyond them: delivery occurs within about a minute, the test is marked with "test": true in the body and an x-agentmart-schedule-test header, and it is never counted as fired or missed. That is exactly the behavioral context an agent needs to trust a test fire won't corrupt schedule state.

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?

One sentence, front-loaded with the action, followed by a tight parenthetical carrying timing and side-effect information. No filler.

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?

Covers what it does, timing, test markers, and state counting, which is strong for a mutation tool. Without an output schema, it does not describe what a successful test fire returns (e.g., a run result or status), a modest remaining gap.

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 100% and documents instance_id, schedule_id, and passport_token fallback. The description itself adds no parameter-level detail, so baseline 3 applies; the body/header injection details are additional behavior, not parameter 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 action (send one test run), the resource (a repeating wake-up/schedule), and the timing (now). The phrase 'exactly like a real run' explicitly distinguishes it from a production firing, which is the key confusion risk among schedule siblings.

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?

Implies usage: fire a test of an existing schedule. But it never names alternatives such as schedule_create, schedule_update, or heartbeat_test, nor states when-not to use it (e.g., don't use for production runs). Context is clear but routing guidance is absent.

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