Get results

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

With no annotations, the description carries the full burden. It usefully discloses the two-phase discovery workflow and the eme_sweep prerequisite, which are non-obvious behaviors. It omits a notable side effect visible only in the schema (results are written to a workspace variable via variable_name) and says nothing about whether calls mutate state or how errors surface for mismatched kind/parameter combinations.

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?

The core action is front-loaded in one sentence, followed by mode-specific instructions, with no filler. The terse pseudo-signature "getemesweep(dataset_name)" is a bit opaque but is compact enough to be acceptable.

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 10-parameter, 12-mode multiplexer with no annotations, covering only two kinds leaves the agent guessing on how to invoke electric, magnetic, dipole_power, source_*, update_index_monitor, and monitor_to_dataset. The output schema excuses it from explaining return values, but the missing side-effect note (variable_name storage) and uncovered kinds make it only minimally sufficient.

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 baseline is 3, and the description earns a bump by explaining how parameters combine per mode: object_name + dataset_name [+ data_name] for kind=data and dataset_name alone for eme_sweep. That cross-parameter pairing logic is not expressed anywhere in the schema's per-field descriptions.

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?

The description opens with a specific verb+resource ("Extract simulation results") and its kind-based routing makes the tool's shape clear. It doesn't explicitly differentiate itself from close siblings like dataset_query or load_data, so an agent may still hesitate between them, but the core purpose is unambiguous.

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?

It gives genuinely useful sequencing for two kinds: list-mode discovery before kind=data, and calling after run_action(eme_sweep). However, ten of the twelve enum values (raw, electric, magnetic, dipole_power, source_*, monitor_to_dataset, etc.) get no usage guidance at all, and there is no when-not-to-use or alternative-tool routing versus dataset_query.

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