Save data

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

No annotations are provided, so the description carries the full behavioral burden, and it only discloses what is written (workspace variables) and that a format is chosen. For a filesystem-writing tool it says nothing about overwriting an existing file at file_path, creating missing directories, or what errors look like — the traits an agent most needs before invoking it.

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?

Two short sentences with no filler: the capability first, then the disambiguation rule. Every clause earns its place.

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?

An output schema exists, so return values need not be explained, and all three parameters are fully documented in the schema. The remaining gap is overwrite/error behavior for a mutation tool with no annotations — minor but not trivial.

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%, with the enum and the 'omit = all' behavior for var_names documented in the schema itself, so the schema does the heavy lifting. The description adds no format syntax, path conventions, or h5 naming caveats beyond what is already structured, so the baseline 3 applies.

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 ('Save workspace variables to a file') and immediately contrasts it with the sibling that handles a related but distinct job ('project_action(save) ... .sim project'). An agent can tell save_data (variable export, with format choice) apart from saving the whole project without opening either 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?

Explicitly names the alternative and the condition that selects it: use project_action(save) when the target is the .sim project, otherwise use this tool for variables. It does not cover when-not-to-use cases such as the target file already existing, but the primary routing decision is resolved.

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