Mne Crop

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

The description discloses that the operation is 'in place', which is a key behavioral trait beyond the schema. However, with no annotations provided, the description carries the full burden. It doesn't mention whether the operation modifies the original object irreversibly, whether it works on all object types equally, or any side effects like data copy behavior. The 'in place' disclosure is valuable but incomplete.

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 sentence that is concise and front-loads the core action ('Crop') and the resource. It earns its place by stating the time window and the in-place behavior. No wasted words, though it could be slightly more structured with usage context.

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 has an output schema and only 3 parameters, the description covers the core operation but leaves gaps: the 'name' parameter is unexplained, and there's no mention of prerequisites (e.g., object must be loaded) or edge cases (e.g., tmin > tmax). The in-place behavior is noted, but for a mutation tool with no annotations, more context about reversibility or object state would be needed for full completeness.

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%, so the description must compensate. It explains tmin and tmax as the time window in seconds, which adds meaning to those parameters. However, the 'name' parameter (default 'raw') is not explained at all—it's unclear whether it's a variable name, a file path, or an object identifier. The description doesn't clarify the role of 'name' in the context of cropping.

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 clearly states the verb 'Crop' and the resource 'Raw/Epochs/Evoked object' with a specific time window [tmin, tmax] seconds. It distinguishes itself from siblings like mne_filter or mne_resample by focusing on time-window cropping, though it doesn't explicitly name a sibling alternative.

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 for cropping MNE objects to a time range, but it doesn't explicitly state when to use this tool versus alternatives like mne_filter (which also operates on time but filters frequencies) or mne_resample. No exclusions or alternative tool names are provided.

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