Plan a run

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is known before reading. The description reinforces this with 'Does NOT submit' and specifies the advisory content of the output, but adds little beyond the annotations about side effects, permissions, or limits.

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?

Two tight sentences with the core promise front-loaded and the scope-limiting clause ('Does NOT submit') at the end where it is most needed. No filler, though it could be slightly more structured for a tool with nine parameters.

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 nine parameters, zero required fields, 22% schema description coverage, and no output schema, the description is thin on the input side: it never explains what an 'intent' is, how the parameters shape the plan, or how defaults apply. It does at least sketch the expected output, but overall it leaves too much unspecified for correct invocation.

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 only 22% (just profile and project), so the description must carry parameter meaning, yet it explains none of the nine inputs. It lists plan outputs (partition, cpus/mem/gpus/walltime) that loosely correspond to parameters like gpuNeed, maxGpus, dataSizeGb, and expectedRuntimeHours, but never maps them or describes format, defaults, or units.

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 names a specific action (turn an intent into a resource plan) and enumerates exactly what the plan contains (CPU vs GPU, partition, cpus/mem/gpus/walltime, smoke-test recommendation) and its form (plain English). 'Does NOT submit' implicitly separates it from the many ris_submit_* siblings, but it never names the closest alternative (ris_estimate_resources) or any other tool, so sibling differentiation is only partial.

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?

Usage is implied rather than stated: by describing a 'safe, validated' plan that 'Does NOT submit,' an agent can infer this is a pre-submission planning step. There is no explicit 'use this when' clause, no exclusion of alternatives such as ris_estimate_resources or ris_generate_sbatch_template, and no stated prerequisites.

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