get_results

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

No annotations are provided, so the description carries full burden. It mentions default file selection and optional summaries, but does not disclose error handling if no _res.m exists, permission requirements, whether reading is destructive, or the format of returned data. Crucial behavioral traits remain undocumented for a tool claiming to 'read' files.

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?

The description is two sentences, front-loading the main action and default behavior, then quickly covering return values and a parameter tip. It is efficient with no wasted words, though it could be slightly more structured with bullet points for return values.

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 values need not be fully detailed, but the description must cover parameter usage and behavioral aspects. With 6 parameters at 0% schema coverage and no annotations, the description is incomplete: it omits guidance on 5 parameters and fails to describe error conditions or output format. The existing output schema mitigates some need, but the overall definition leaves an agent guessing about key invocation details.

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 only partially compensates by explaining the 'variables' parameter ('Use variables=[...] to extract specific _res.m variables') and implying 'file' or 'workdir' via defaults. Five other parameters (file, input, workdir, max_rows, sections) receive no explanation, leaving significant gaps for an agent to interpret their purpose.

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 states a specific verb and resource: 'Read and summarise Serpent output files', naming the exact file type (_res.m) and the specific outputs returned (k-eff, run parameters, integral rates). It distinguishes itself from sibling tools like plot_results and job_output by focusing on Serpent result extraction, though it could more explicitly contrast with plot_results.

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 through default behavior ('Defaults to the newest _res.m') and a specific scenario for variables extraction, but no explicit when-to-use versus alternatives (e.g., plot_results or job_output) is provided. An agent must infer that this is for programmatic result reading rather than visualization.

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