get_band_power

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 adds some useful context about the relative values being immune to impedance drift, which is a meaningful behavioral trait. However, it doesn't disclose return format details (though an output schema exists), any side effects, or error conditions. Given the useful impedance-drift insight but absence of broader behavioral details, a 3 is fair.

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 compact—three sentences. The first sentence is a clear purpose statement, the second identifies the tool's role, and the third provides actionable guidance. No filler or redundancy. It could arguably drop the 'workhorse' framing, but that framing also serves usage guidance. Efficient and front-loaded.

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?

The tool has 6 parameters, an output schema, and no nested objects. The description covers the core purpose, provides domain guidance (relative values immune to drift), and the schema covers all parameters. With an output schema present, return-format explanation isn't required. The main gap is no guidance on trade-offs versus get_psd for spectrum analysis, but the description is reasonably complete for its complexity level.

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 100%, so the schema fully documents each parameter. The description adds value by clarifying the _rel parameter's significance for threshold stability over time, which complements the schema's 'fraction of total power' wording. This extra guidance justifies a 3 rather than baseline 3 being penalized, but it doesn't substantially enrich parameter understanding beyond the schema.

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?

Description states 'Band power over the most recent window, per channel and averaged' and calls it 'the workhorse feature for neurofeedback and closed-loop triggering.' This clearly indicates verb (get/compute) + resource (band power) in a specific usage context. It doesn't explicitly distinguish from get_psd (which is its closest sibling), but the purpose is clear and specific.

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 gives clear context on when to use it ('the workhorse feature for neurofeedback and closed-loop triggering') and importantly recommends using _rel values for thresholds because they're 'largely immune to impedance drift.' This is practical guidance on how to use the output. It doesn't explicitly state when NOT to use it or name an alternative like get_psd, slightly reducing the score.

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