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

The description explicitly states that this tool writes state: it creates a monitor, and 'a rejected creation writes no monitor or event' implies successful creation does write. The annotations declare readOnlyHint=true, so the structured metadata mislabels a state-creating call, which is exactly the contradiction case. The description's own disclosure is detailed (idempotency, free-tier gating, 402 with accepts[], normalization), but the conflict with the annotation is disqualifying for this dimension.

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-loaded with the core action and identity rule, then limits, transport, and errors in a workable order; the example and error table both earn their place. There is redundancy — 'The same slug uses the same monitor' is restated as 'the same slug always means the same monitor, so a retry never creates a second one' — and the error sentence is a dense run-on.

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 supplies the return shape ({ ok, endpoint_id, created }), the failure modes with codes (400, 402, 404) and their remediation, and the free-tier write constraint. Nothing an agent needs in order to call this correctly is missing, apart from the annotation mismatch noted elsewhere.

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 baseline would be 3, and the description adds real meaning on top: slug is normalized to lowercase [a-z0-9-] capped at 40 chars, it becomes both the monitor name and its identity, and the curl example shows extra query arguments (cron, tz, grace_sec) that the input schema does not expose. That extra semantics — plus the error names slug_invalido, cron_invalido, tz_invalida — genuinely helps an agent construct a valid call.

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 states a specific verb and resource — 'Create a monitor on its first check-in' via a slug ping — and defines the identity rule (same slug = same monitor) plus the transport ('Works by GET or POST'). It never names the sibling it should be preferred over (create_endpoint, ping_ingest, signal_slug), so it falls short of full sibling differentiation.

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?

Usage context is strong on constraints — creation happens only inside the free tier or trial, retries are safe, past the tier you get a 402 — but it gives no routing guidance telling an agent when to pick this over create_endpoint or the other signal_* tools. The when-not is clear; the when-versus-alternatives is absent.

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