Run a SCAPS script

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

Goes well past the annotations, which only flag destructiveHint=true. It discloses implicit script mutation (server prepends 'quit', error-log settings, and 'clear all'), a validation gate against the installed SCAPS version, sandboxing rules (bare file names, system commands rejected), and the mechanism by which outputs are collected ('save results.<kind> name'). That explains both why the call is destructive and how to retrieve artifacts.

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?

Purpose is front-loaded in the first clause, then a compact block of execution constraints follows with no filler sentences. Slightly dense as a run-on of constraints, but every clause carries information an agent needs.

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?

With an output schema present, return values needn't be explained, and the annotations carry the safety profile. The description covers prepended commands, validation, sandbox rules, and result collection; the only gaps are the long-run job handoff and timeout semantics, which are covered by the schema.

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 100%, so script, timeout_s, wait_seconds, and validate_only are already documented in the schema. The description adds nothing parameter-specific — neither the wait/job-continuation tradeoff nor validate_only is referenced in prose. The 'save results.<kind> name' note describes script content, not an input parameter.

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 ('Run a SCAPS script') and immediately scopes it against the sibling family with 'for workflows beyond the other tools', then enumerates the escape-hatch use cases (recorder, curve fitting, math, loops, tandem). An agent can distinguish this from scaps_simulate, scaps_batch, or scaps_optimize 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?

'For workflows beyond the other tools' clearly signals this is the fallback/general-purpose tool rather than a first choice, and the enumerated use cases make the intended context concrete. It stops short of naming which specific sibling to prefer for common cases (e.g. 'use scaps_simulate for a single IV curve'), so the exclusions remain implicit.

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