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

Annotations declare destructive/non-idempotent/open-world, and the description goes beyond them with scheduling behavior (first check on the next tick, within five minutes), rate/tier limits, the API-key requirement, and the shape of the return payload. It still doesn't say what happens on a slug/name collision or whether repeated calls create duplicate targets, which matters given idempotentHint=false.

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?

Dense but front-loaded: enrollment scope first, then same-call checks, then return payload, then timing, then tier limits, then the auth prerequisite. Every sentence carries information, though the long parenthetical enumerations make it heavier than it needs to be.

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 15-parameter, nested-object creation tool with no output schema and no output description, the description does the important work: it explains what is returned, the async first-run timing, the auth requirement, and the tier floors that bound intervalSec. Remaining gaps (collision behavior, whether duplicate enrollments are rejected) are minor but real.

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 and the schema already carries kind, url, auth, alerts, checks, modelVar, etc. The description adds only one behavioral note about parameters — that passing `checks` creates them in the same call and that POST /api/v1/probe proposes three — so it does not meaningfully exceed the schema for the other 14 parameters.

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 first sentence states a concrete verb (enroll) and enumerates the exact resource types it accepts — http endpoint (JSON or OpenAI-style chat), remote MCP server (Streamable HTTP url), or A2A agent. It also states what comes back (target id, status page, badge SVG, README snippet), so an agent can distinguish it from siblings like agentcheck_add_check 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?

It gives real usage context: call agentcheck_run_now to run immediately instead of waiting up to five minutes for the next tick, and it surfaces tier constraints (Free: 1 target hourly; Starter+: 5-minute checks). It does not, however, say when NOT to use it — e.g. that adding checks to an existing target is agentcheck_add_check's job.

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