Sample a stored result

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description still adds real context beyond them: the 'repeatable random sample' (determinism of randomness), the 1-50 bound, and the fallback to storage order when no time column exists.

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 dense sentence with the core action front-loaded and the modifiers (method, n bound, column subsetting) trailing in priority order. No filler or redundancy.

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 four-parameter, read-only tool with no output schema, the description conveys the essential shape of the result (n rows, optionally a column subset). It does not describe ordering guarantees or how the sample relates to the underlying result_id, but nothing critical for calling it correctly is missing.

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 100%, so n, method, columns, and result_id are already documented in the schema, making 3 the baseline. The description's only marginal addition is that the random method is repeatable, a nuance the enum label 'random' does not convey.

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 (Show) and resource (n rows of a stored result) with the sampling scope spelled out (first/last/random, optional column subsetting). It reads clearly as a preview/sampling tool, distinguishing it from full-query siblings like results_query and results_describe without needing to name them.

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 'Show n rows ... of a stored result', which signals a preview/sampling purpose, but there is no explicit when-to-use guidance or routing to alternatives such as results_query. The agent must infer that this is for inspection rather than full data retrieval.

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