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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered structurally. The description adds real value beyond that by explaining the mechanism ('Reads the heartbeats recorded under the key; silence is the alarm') and that a signed receipt is returned.

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 core question is front-loaded, followed by usage triggers and mechanism in tight sentences. The conversational human-utterance examples earn their place as routing cues; the only slight cost is a chatty register rather than terse specification.

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 annotations covering the safety profile and no output schema, the description supplies what an agent needs: what it checks, the time-window concept, that absence of heartbeats signals failure, and that a signed receipt comes back. It is complete enough for a simple two-parameter read 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 coverage is 50%: 'cle' has no schema description while 'depuis' is documented (window in seconds, default 86400). The description loosely ties 'the last N seconds' to the window and 'under the key' to the key, adding marginal meaning, but it does not fill the gap for the undocumented required 'cle' parameter. Baseline 3 for mid 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?

The description states a specific verb+resource: it confirms whether a scheduled task ran within a time window by reading heartbeats under a key. An agent can tell it verifies task execution, but it never explicitly contrasts itself with the sibling confirme_* tools (battement, courriel, domaine, page, sac), so sibling differentiation is only implicit.

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 concrete when-to-use triggers ('did the report go out?', 'is the automation still running?', before answering 'yes, it ran'), which maps well onto the agent's decision context. It stops short of naming an alternative tool or stating when NOT to use it, so it stops at clear context without exclusions.

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