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

With no annotations, the description carries the full burden and does so thoroughly: it discloses that start does not clear the miss counter, does not move last_event_at, that the next success closes the run and records last_duration_ms, and how max_duration_sec triggers an alert. This is substantial behavioral context beyond the bare schema.

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 description is front-loaded with the core purpose and contains dense, useful information. However, it is redundant: the point that start does not clear the dead-man clock / miss counter and that a hanging run still becomes a miss is made twice, as is the fact that the next success records duration. Shorter would be clearer.

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 tool with subtle monitor semantics and no output schema, the description covers the critical operational details: dead-man clock behavior, overlap-safe rid handling, duration recording, and max_duration_sec alerting. It is nearly complete, though it does not describe the response format or explicitly explain the relationship to sibling signal tools.

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?

The schema already documents the only parameter `id` fully as "Monitor ID, from Monitor.ingest_url," so schema coverage is 100%. The description adds useful context about the `?rid=` query parameter for overlapping runs, but does not add new meaning about the `id` parameter itself. Baseline 3 is appropriate.

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 opens with a specific action, "Says the run STARTED," and clarifies the tool's role by explaining what it does and does not do (does not clear the dead-man clock, does not move last_event_at). It is clear enough to stand apart from signal_exit_code and signal_fail, though it never names or explicitly contrasts those 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?

The description implies the tool should be called when a run starts and provides conditional guidance for using `?rid=` when runs can overlap. However, it does not explicitly state when to prefer this tool over signal_exit_code or signal_fail, nor does it provide exclusions or alternative routing.

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