mne_make_epochs

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

With no annotations, the description carries the full burden of behavioral disclosure. It goes beyond a simple definition by explaining the baseline default, event_id format, reject threshold in volts, and that the output is stored under epochs_name. This gives meaningful insight into the tool's behavior, though it doesn't state whether the Raw object is mutated or if specific permissions are needed.

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 description is a single, slightly run-on sentence, but it is front-loaded with the core purpose and efficiently packs parameter semantics into a compact form. Each clause adds valuable information, and it avoids unnecessary detail. It earns its place, though a cleaner structure (e.g., separate sentences) would improve readability.

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?

Given the tool's complexity (8 parameters, 0 required) and no annotations, the description covers the most important parameters and gives a clear overview. However, it omits any explanation of events_name and does not mention workflow context such as needing to find events first or that this step precedes plotting/averaging. It is adequate but not fully complete.

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?

The input schema has 0% description coverage, so the description must compensate. It effectively explains tmin/tmax (seconds relative to event), baseline (default value), event_id (format and purpose), and reject_eeg (threshold in volts with example). It also indicates the output variable via epochs_name. However, events_name and raw_name are not explicitly described, leaving a small gap.

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 and resource: 'Segment a Raw object into Epochs around events.' This clearly identifies the tool's primary function and differentiates it from siblings like mne_plot_epochs_image or mne_average_evoked, which operate on already-created epochs.

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 description implies usage: to create epochs from raw data, you use this tool. It provides detailed parameter usage (e.g., tmin/tmax, baseline, reject_eeg) but does not explicitly state when to use it over alternatives, nor does it mention exclusions or prerequisites. The 'Segment' verb implies the primary context, but no explicit when/when-not guidance is given.

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