md_run_report

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the verdict vocabulary (GO/FINISHED/INCOMPLETE/CRASHED) and the side effect of optionally logging to the registry, but never states whether it is read-only, whether it writes report files into the run directory, or what permissions/registry state the log step touches.

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?

One sentence plus a short clause, with the resource and the output list front-loaded and no filler. The trailing 'Optionally logs to the registry' reads as an afterthought rather than being integrated, a minor structural blemish.

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 restated, and the description covers the report's scope and verdict taxonomy. Given the tool has a side effect (registry logging) and no annotations, more disclosure on mutation/reversibility and run_dir requirements would be needed for a 5.

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%, but with only two parameters the description mostly compensates: it maps the 'log' flag to 'Optionally logs to the registry', clarifying an otherwise opaque boolean, and the enumeration of artifacts implies what 'run_dir' must contain. It never spells out run_dir's structure or the log default, keeping it just short of full coverage.

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 ('Analyze') and resource ('a GROMACS run directory') and enumerates the concrete outputs it produces: RMSD verdicts, .xvg inventory, md.log crash scan, artifact presence, and a verdict. This makes clear it is an aggregate run-level report rather than the single-metric siblings like rmsd_summary or xvg_summary.

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?

Implies usage ('analyze a GROMACS run directory') but names no alternatives or when-not conditions, even though siblings such as rmsd_summary, xvg_summary, and compare_runs overlap with parts of what it computes. The agent can infer it is the whole-run option but gets no explicit routing guidance.

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