compare_runs

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, yet it only enumerates output metrics (plateau status, late-run means, drift, relative difference) that the output schema already covers. It says nothing about side effects, read-only nature, what happens with incomplete runs, or failure behavior.

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?

A single front-loaded sentence that names the operation, the two inputs, and the returned verdicts with zero filler. Every clause 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?

For a two-input comparison tool with an output schema, the description is minimally adequate: the return values are covered elsewhere and the core purpose is stated. However, with no annotations and no parameter documentation, it leaves open whether the tool performs fresh computation, what the directories must contain, and how mismatched or partial runs are handled.

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 parameters are bare ('Dir A', 'Dir B'), so the description must compensate. It adds only that these are 'run directories' with a loosely illustrative 'apo vs holo' example, but gives no path format, structure expectations, or ordering semantics for the two arguments.

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 gives a specific verb+resource ('Side-by-side RMSD verdicts for two run directories') plus an example of the comparison axis (apo vs holo), so an agent knows exactly what it computes. It does not explicitly distinguish itself from nearby siblings like rmsd_summary or compare_plot, which keeps it from a 5.

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?

There is no statement of when to use this versus rmsd_summary (single-run RMSD) or compare_plot, and no prerequisites such as whether both directories must already contain completed analyses. Usage is only implied by the word 'compare'.

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