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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavioral context: unknown ids are not an error but yield an 'untested' verdict, mc narrows to exact-version runs, and clash takes precedence if any run clashed. However it does not describe the shape or size of the returned run list, so this is solid supplemental context rather than exhaustive.

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?

Front-loads the outcome definition, then prerequisites, semantics, and precedence rules, closing with the return summary. Sentences are dense but each carries distinct information; no repetition of annotation or schema content.

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?

Covers the outcome vocabulary, the untested/unknown-id edge case, the version-narrowing parameter, ordering insensitivity, and precedence of clash, with an output schema handling return details. Nothing an agent needs to invoke or interpret this correctly appears to be missing.

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 100%, so parameter formats are already documented. The description nevertheless adds non-obvious semantics beyond the schema: the two ids are interchangeable ("any order"), ids may come from names via search_mods, and mc restricts to exactly one version. That exceeds the baseline for a fully covered schema.

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 verb-and-resource pair (compare whether two mods ran together) and enumerates the possible outcomes: worked together, clashed, or never tested. It also names the sibling it is not (get_mod_runs) for the one-mod case, so an agent can route between them without opening schemas.

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?

Gives explicit triggering scenarios ("can I use X with Y?", or two suspects from diagnose_crash) plus an explicit alternative (get_mod_runs for one mod's whole record) and a prerequisite (call search_mods first if unsure of ids). When-to-use, when-not, and alternatives are all present.

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