sim_setup_analysis

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

With no annotations, the description carries the whole load and does so well: it discloses that a script-started run performs operating point, DC sweep, transient and AC together regardless of the dashboard, that Altium's own settings are saved first and the file is reloaded afterwards, and that a missing .simcfg is created. It also names the mutation target and the exact return keys (simcfg, set, reloaded, created).

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 a one-line summary, then value format, args, and run behavior — a sensible order. There is mild redundancy (re-stating that the analyses set here are what the run uses, and a block-caps 'WHAT A RUN DOES, MEASURED' heading) but nothing is 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 mutation tool with five loosely typed params, no annotations and no documented schema properties, the description covers input semantics, side effects, file creation, reload behavior and return keys. An agent has everything needed to invoke it correctly without opening other tools.

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% and the nested objects have no declared properties, so the description supplies all meaning: SPICE value formats with SI suffixes ('5u', '100meg'), defaults (start=0, max_step=step), the ac sweep enum semantics (points per decade/octave vs total for lin), dc source as a designator or 'Temp', output expressions, and project_path defaulting to the focused project.

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?

Opens with a specific verb+resource+location: sets the analyses that sim_run uses, written into the project's .simcfg. It explicitly names sim_run and later sim_get_results(analysis=...), so an agent can place it in the simulation workflow rather than confusing it with the other sim_* siblings.

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?

The framing 'Set the analyses sim_run will use' establishes this as a configuration step that precedes a run, and the note that an unneeded analysis 'still runs on its last settings' with sim_get_results returning just one is useful routing context. It does not spell out an explicit precondition/ordering ('call before sim_run') or when-not to call it, so it stops short of the top band.

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