build_on_node

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

Annotations only declare readOnlyHint=false and destructiveHint=false. The description adds valuable non-obvious behavior: execution is synchronous and capped at 15 minutes, and it runs remotely via srun. It stops short of stating what gets written where or failure semantics.

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 dense sentences, front-loaded with the action, then the critical arch rationale in caps, then the execution constraint. Every sentence earns its place.

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?

Output schema exists, so return values need no explanation, and the description covers purpose and key constraints well. However, for an 8-parameter tool with zero schema documentation, the description leaves the bulk of invocation semantics unexplained.

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 8 parameters, so the schema explains nothing. The description only loosely gestures at the arch parameter ('architecture voulue') and the minutes cap; cpus, modules, workdir, commands, with_gpu and spack_packages get no meaning at all.

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 pair (compile/install) and resource (compute node of the desired architecture) plus the mechanism (srun). It clearly separates itself from login-node siblings like run_login_command and build_wheel by naming the target environment.

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?

Gives a strong when-to-use rule: INDISPENSABLE for GPU nodes because they are aarch64 while the login node is x86_64, so login-produced artifacts are unusable. It implicitly contrasts with login-node work but never names an alternative tool explicitly to route the agent.

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