Set numerics

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

Goes well beyond the annotations (readOnly=false, idempotent=true, destructive=false) by disclosing that omitted fields keep the FDS default for the current SIMULATION_MODE, that particle_global_unset restores keys to FDS defaults, that MP5 is unsupported and silently falls back to CHARM with a warning, and that lock_time_step requires dt. These are real behavioral traits an agent cannot infer from structured fields.

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-loaded with the purpose and the when-to-use trigger before the denser namelist bookkeeping. The particle_global sentence is long and enumerates many keys, but each clause carries distinct information; the trailing bulc rule-IDs line is useful routing rather than filler.

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 9-parameter, mostly-optional mutation tool with a nested object and no output schema, the description covers the essential gaps: default inheritance for omitted fields, the dt requirement for lock_time_step, unset semantics, and engine-specific fallbacks. An agent has enough to call it correctly without further documentation.

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 the schema already documents each parameter; the baseline is 3. The description adds cross-cutting semantics the schema lacks: the &TIME/&MISC namelist mapping, the omit-keeps-default rule scoped to SIMULATION_MODE, and the grouping of particle_global keys versus particle_global_unset.

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 with scope: "Set numerical stability controls (time step and advection scheme)", and clarifies which namelists (dt/lock_time_step to &TIME, the rest to &MISC) it touches. It does not explicitly distinguish itself from nearby siblings such as set_time or set_run_options, which an agent could plausibly confuse with a numerics tool.

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?

"Use this when a run diverges, produces NaN, or when matching CPU FDS settings" gives concrete triggering conditions, and lock_time_step is labeled the "standard remedy for a diverging case." No alternative tool is named (e.g. get_numerics as the read counterpart, or set_time for simulation time), so routing is implied rather than explicit.

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