plot_results

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

With no annotations, the description carries the full burden. It does disclose the key side effect ('Returns the path of the written image'), which tells the agent a filesystem write occurs, but it says nothing about where the file lands, whether it overwrites an existing output, permissions, or whether the source data must already exist from a prior run.

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 dense sentences with zero filler: the purpose leads, then the per-kind requirements, then the return value. Every clause carries information an agent needs before calling.

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 the return-path sentence is arguably redundant, and the description need not restate return structure. But for a 9-parameter, annotation-free tool with 0% schema coverage, more than half the parameters remain semantically opaque, leaving the agent under-informed for a write-side-effect operation.

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 coverage is 0% across 9 parameters, so the description must compensate. It explains the required 'kind' values and the conditional dependencies ('detector needs name', 'variables needs x and y'), which is meaningful semantic content, but leaves file, input, output, workdir, and lang entirely undefined.

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 and resource ('Draw a PNG plot from Serpent output') that clearly separates it from the sibling set (run, get_results, job_output, etc.), which contains no plotting tool. It stops short of explicitly naming an alternative it might be confused with, but the action is unambiguous.

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 kind enumeration functions as de facto usage guidance: it tells the agent which kind to pick (detector, keff, burnup, variables) and the conditional prerequisites for two of them. However, there is no guidance on when to reach for plot_results versus the sibling get_results or job_output, nor any prerequisite/ordering context.

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