run_cluster_sanity_check

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

readOnlyHint=true already establishes the safe-read profile, so the description is not obligated to restate safety. It adds genuine behavioral context: the failure mode is silent slowdown rather than a crash, and the output is a ready-to-use --exclude clause for suspect nodes. It does not mention runtime cost or how long a sanity sweep takes.

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?

Three tight sentences with no filler: what is checked, why it matters, and what comes back. The important scoping information is front-loaded before the rationale.

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?

An output schema exists, so return-value detail is not required, though the description helpfully previews the --exclude output. The gap is on the input side: with zero schema description coverage and undocumented parameters like check_type and minutes, an agent cannot confidently set non-default values.

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% across four parameters, so the description must compensate and largely does not. 'Un ou plusieurs noeuds' loosely maps to the nodes parameter, but minutes, max_nodes, and check_type (whose enumeration of allowed values is undisclosed) are never explained.

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 verb (verifie/verify) and a precisely scoped resource: GPU health on one or more nodes, enumerating the exact conditions checked (thermal/power throttling, uncorrected memory errors, abnormal frequency). This distinguishes it from general health siblings like job_system_health or romeo_selfcheck, and signals its Slurm-oriented output (--exclude clause).

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?

Explains the motivating scenario clearly: a degraded node does not crash but silently slows a distributed job, which tells the agent to run this before submitting spread work. No explicit 'use X instead of Y' routing versus siblings such as diagnose_job or job_system_health, so it stops short of a 5.

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