read_window

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It transparently discloses the decimation/limit behavior ('Long windows are decimated to max_samples per channel'), the filtering behavior depending on filter chain state, and the data-quality tradeoff. It doesn't mention the return format in detail, but an output schema exists to cover that.

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—two short sentences plus a parenthetical—with zero wasted words. Every sentence adds value: first states purpose, second discloses behavior and provides navigation to alternatives. Front-loaded with the primary action.

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 output schema exists, return-value explanation is not needed. The description covers the key behavioral caveats (decimation, filtering dependency) that an agent must understand to use the tool correctly. The alternative-tool guidance fully compensates for the tradeoff introduced by decimation. Complete for a signal-read tool with this level of complexity.

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 baseline is 3. However, the description adds meaningful context beyond the schema by explaining the decimation interaction with max_samples and explicitly steering toward alternatives for full-resolution numeric work. The filter chain dependency of the `filtered` parameter is also contextualized.

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 uses a specific verb+resource ('Read the most recent samples from the buffer') and clearly distinguishes this from sibling tools by explicitly contrasting with get_band_power and get_psd. It specifies the read-only nature and buffer scope with high precision.

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 explicitly states when NOT to use this tool ('for numeric work prefer get_band_power or get_psd'), names the alternative tools directly, and explains the context (filtered vs raw, decimation). It also references set_filters as a precondition, providing clear guidance on the workflow.

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