job_live_metrics

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

Annotations only assert readOnlyHint=true; the description adds real behavioral context beyond that — it is instantaneous/non-blocking, requires no log reading, and does not need the job to finish. It does not cover edge behavior such as what is returned when the job has already ended, so it is strong but not exhaustive.

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?

One front-loaded sentence captures the core purpose and scope, followed by a second sentence covering diagnostic value. Dense but every clause earns its place; the only mild cost is the length of the enumeration.

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 an output schema present, return values need not be explained, and the description adequately conveys what is measured and why. Missing only operational caveats such as prerequisites (job must be running) or behavior for a completed job.

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 0% and the description never mentions the job_id parameter or its format. The single required parameter is largely self-explanatory from its name, so this is acceptable rather than damaging, but the description contributes no meaning beyond the schema.

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?

States a specific resource and mode ('Telemetrie instantanee d'un job EN COURS') and enumerates exactly what it reports (GPU occupancy/memory, temperature, power, top processes). It also carves itself out from siblings by specifying 'sans lire de journal ni attendre la fin', which separates it from log-reading and wait-for-completion tools.

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 phrase 'sans lire de journal ni attendre la fin' implicitly routes the agent here instead of job_output or wait_for_job, and it names two concrete diagnostic situations (I/O-sleep while GPUs reserved, VRAM-saturation climb). It stops short of explicitly naming the alternative tools or stating prerequisites such as the job needing to be active.

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