surrogate_predict

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety bar is low. The description still adds real behavioral value: out-of-range inputs are rejected, the error bar covers interpolation only, the answer carries mesh error from the underlying solves, and no material/support/real-part validation is performed.

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?

Three tight sentences, front-loaded with the benefit and the no-solve guarantee, then caveats. Dense but every clause carries information; the parenthetical 'see mesh in the result' earns its place by explaining where the caveat is visible.

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?

There is no output schema, and the description partially compensates by pointing to 'mesh in the result'. For a 4-parameter prediction tool with nested values the coverage is good, but the role of `outputs` and `language` remains unexplained.

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%, so the description must compensate, and it does explain the critical `values` parameter as {parameter path: number} in the units fixed at build time. However `study_id`, `outputs` and `language` (the one enum) get no explanation at all, leaving a substantial gap.

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 (answer from a finished surrogate) plus the defining property: milliseconds with no solve. That contrast implicitly separates it from run_simulation and build_surrogate, so an agent can pick it without opening a schema.

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 context is clear: call this when a surrogate already exists and speed matters, and it explicitly notes it refuses inputs outside the built ranges. It stops short of naming build_surrogate or surrogate_status as the alternative when no finished surrogate exists.

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