Mne Events From Annotations

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

With no annotations provided, the description carries the burden of behavioral disclosure. It clearly states the transformation and the output shape, but it does not mention whether the Raw variable is modified, how annotations map to event IDs, or what happens if no annotations exist.

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?

A single front-loaded sentence states the operation, inputs, outputs, and target file formats with no wasted words. It is concise and effective.

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 tool with no annotations and zero parameter documentation, the description omits key details needed to invoke it correctly, especially parameter meaning and when to choose this over mne_find_events. The output schema may document the return shape, but the usage gap remains significant.

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 0%, and the description never explicitly explains raw_name or events_name. The defaults and naming hint at a source variable and an output variable, but the agent must infer this connection.

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 names a specific verb ('Convert'), a specific resource ('a Raw object's annotations'), and the concrete outputs ('events array + event_id map'). The parenthetical formats also help differentiate it from sibling mne_find_events, which likely derives events from stimulus channels rather than annotations.

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 this is the right tool when annotations carry event information, especially for EDF/BrainVision/EEGLAB data. However, it never explicitly contrasts it with mne_find_events or states when not to use this tool.

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