Read a window of a result

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

Annotations already cover the read-only/idempotent/non-destructive profile, yet the description still adds non-obvious behavior: values are truncated when read inline but complete in downloads, and the returned payload shape depends on the result kind. It stops short of describing pagination boundaries or what happens past the end of a window.

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?

A single front-loaded sentence with the general case first, then the mode-specific exceptions, then the truncation caveat. Dense but every clause carries information; slightly cramped to read in one pass.

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?

For a 7-parameter, no-output-schema read tool, the description covers both result modes, the column selection option, and the truncation tradeoff — enough to invoke correctly. Gaps are minor: no hint about where resultId originates or what an out-of-range window returns.

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 coverage is only 29%, so the description carries real weight — it maps offset/limit/columns to the row mode and file/lineOffset/lineLimit to the blob text mode, and clarifies that 'file' comes from a listing row. The one required parameter, resultId, gets no explanation in either place.

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 ('Returns one window of a result inline') and immediately distinguishes the two payload shapes: tabular rows vs. blob files/images. It does not name a sibling tool, so an agent must infer the boundary with get_result and describe on its own.

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?

Usage is implied by the mode enumeration — use offset/limit for row results, file + line range for blob text, file alone for images — and 'downloads keep full values' hints at when to prefer a download instead. However, no alternative tool is named and there is no explicit 'use this when' statement.

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