Chainsaw: result fields

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuine behavioral detail beyond that: it is a sampling operation ('sampled rows') and returns counts plus an example per path, which the agent wouldn't know from annotations alone.

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?

Two short sentences, output shape front-loaded first and the motivating use case second, with no filler.

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 2-param read-only tool with full schema coverage and no output schema, the description is nearly complete: it covers purpose, why to call it, and the shape of the return value. Only the relationship to overlapping siblings (e.g. result_summary) is left unaddressed.

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% and both parameters are self-documented, so baseline is 3. The description's phrase 'sampled rows' loosely evokes the sample parameter but adds no syntax, bounds, or default information 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?

States a specific verb and resource: discover the field paths present in a result. The 'so you can project or group on them' clause scopes the purpose to schema discovery rather than row retrieval, which inherently distinguishes it from the result_events/page/chunk siblings.

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 clear context for when to use it (before projecting or grouping) but names no alternatives or exclusions, so the agent must infer that siblings like result_summary or result_page are not the right call here.

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