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

The description adds substantial behavior beyond the readOnlyHint annotation: it explains the asynchronous status: 'running' path with polling via get_task_results, the empty-array result when no quotable evidence exists, and the exact quote block format. This is far more than the annotation alone communicates.

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 well front-loaded and organized into purpose, usage, and output-format sections, but it repeats the same idea several times: line-tied quotes are mentioned in the opening line, the second sentence, and again in the third sentence. Each point is useful, but the redundancy is noticeable.

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?

Despite having no output schema, the description fully explains return shapes, empty results, line-range indexing format, and async polling. Given the tool's complexity — 4 parameters, 3 modes, async behavior, and no output schema — nothing necessary for a correct call or interpretation 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?

The input schema is fully documented, so the baseline is 3; the description goes beyond it by tying mode values to concrete output shapes ('In quotes and both modes the output is quotes: [{ id... }]') and clarifying the polling contract for maxWaitSec. It does not deeply re-explain each parameter, but the schema already handles that.

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 opens with a specific verb and resource: 'Answer from collected records, with quotes tied to exact lines.' It clearly distinguishes the tool from siblings by contrasting it with grep_collected_records and read_collected_records, and by emphasizing synthesis over exact matching or direct reading.

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?

It explicitly states when to use the tool ('material too large to fit in context', 'evidence has to hold up') and when not to ('exact wording or counting occurrences', 'material small enough to read directly'), naming the alternative tools for those cases. This gives an agent decisive routing criteria.

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