mne_filter

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

With no annotations, the description carries the full burden. It discloses the critical trait 'in place,' indicating the object is modified. However, it does not state what happens when both l_freq and h_freq are null, whether the function returns a value, or potential side effects. These gaps leave some behavioral aspects unclear.

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 two sentences, front-loaded with purpose and the key 'in place' behavior, followed by concise parameter explanations. Every word adds value with no repetition or fluff.

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?

Despite no annotations, the description covers the main purpose, key parameters, and the in-place mutation. It is adequate for a moderate-complexity tool, though it omits edge cases (e.g., both frequency edges null) and the use of the 'name' parameter. The presence of an output schema means return-value details need not be repeated.

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 description explains four of five parameters: l_freq, h_freq, notch, and picks, including allowed values for picks. Since schema coverage is 0%, this is essential. However, the 'name' parameter (likely identifying the object) is not explained, leaving a minor 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 clearly states the tool's function: 'Band-pass / high-pass / low-pass and/or notch filter a Raw/Epochs/Evoked object in place.' This is specific with a verb and resource, and it distinguishes from sibling tools like mne_resample or mne_plot_psd by focusing on filtering.

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 when to use the tool (when filtering is needed) but does not explicitly mention alternatives or exclusions. It provides parameter details but no guidance on choosing this over other MNE tools, such as 'use this to remove line noise instead of mne_resample.' The usage context is only indirectly conveyed.

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