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

Annotations already declare readOnly/idempotent/non-destructive, so safety needs no restating. The description adds a genuinely valuable behavioral caveat beyond the annotations: the loader ASSUMES volts, so µV-native files read 1e6x too large, with the fix (unitsScale in custom_data config). It does not mention cost/latency for multi-subject cohort loads, which is a minor remaining gap.

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?

Front-loaded with the return content, then usage rationale, then parameter/units notes — a sensible order with no filler sentences. It loses a point because the mode/subject/dataset explanations duplicate what the input schema already states verbatim.

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?

An output schema exists, so return format need not be explained, and the description covers purpose, when-to-use, parameter defaults, and the units gotcha. For a three-parameter read-only inspection tool this is fully sufficient to call correctly and interpret the result.

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% and the schema already documents the defaultSubject fallback, the comma-list cohort form for subject, and the training|evaluation|all enum. The description largely restates those semantics (only adding the 'S01' example), so it adds minimal meaning beyond the structured fields. A 3 is the correct baseline when the schema carries the parameter documentation.

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?

States a specific verb and resource ('Exploratory summary of a public EEG dataset') and enumerates exactly what is produced: channels, sampling rate, trial/class balance, per-channel µV stats, band powers, PSD. This distinguishes it cleanly from siblings like data.inspect_file (file-level) and plots.dataset (visualization) without needing to open either schema.

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?

Gives explicit when-to-use guidance with rationale: 'Look at the data BEFORE building pipelines', and explains why each output matters (class balance drives stratification, flatlined channels signal montage/reference problems). It also cross-references catalog.datasets for the defaultSubject default. It stops short of naming when NOT to use it or pointing to an alternative sibling (e.g., plots.dataset for visualization), so it is not a full 5.

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