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

Annotations declare this is a non-idempotent write in an open world, but the description adds substantial behavior beyond that: the exact response contents (target id, public status page, badge SVG, README snippet), the next-minute-tick scheduling semantics, the free vs Starter+ interval floors, and "Requires an API key". Credential handling ("Stored encrypted and never returned or logged") is also surfaced in the schema, reinforcing the safety profile.

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 action, then orders sentences by task flow: what to enroll, the checks shortcut, what comes back, when it runs, tier limits, auth requirement. Each sentence carries distinct information with no redundancy.

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?

With no output schema, the description compensates by enumerating the return values (target id, status page, badge URL, README snippet). Combined with the auth requirement, scheduling tick, tier limits, and the explicit alternative for immediate runs, an agent has everything needed to invoke and interpret this 15-parameter, nested-object tool.

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%, so the baseline is 3, but the description adds real semantic value beyond the fields: it clarifies that `checks` creates checks in the same call and that the probe endpoint proposes three, and it explains the interval-floor rule ("Free hourly, Starter+ 5 min") that governs `intervalSec`. It does not, however, touch the many other parameters (auth, alerts, modelVar, corpusUrl), which is acceptable given full schema coverage.

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?

Opens with a specific verb+resource ("Enroll something to monitor") and immediately enumerates the three monitorable kinds (http endpoint, remote MCP server, A2A agent), which matches the `kind` enum in the schema. An agent can distinguish this from sibling tools like agentcheck_add_check or agentcheck_run_now without opening the 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?

States when to use the same-call path ("Pass `checks` to create checks in the same call") and names the alternative for immediate execution ("call agentcheck_run_now to run immediately"). It also notes tier-based scheduling limits, but does not explicitly route to agentcheck_add_check for adding checks to an existing target, leaving one gap in the when/when-not picture.

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