narrow_file

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

With no annotations provided, the description carries the full behavioral burden and does so well. It reveals that output is verbatim, line-numbered spans, that summaries are never produced, that results are verified against the original file, and that source code files are refused.

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 tightly written sentences with no wasted words. The core input-output behavior is front-loaded, followed by the refusal rule and alternative, making the description easy to parse quickly.

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?

The description is complete for a simple 2-parameter tool: it states inputs, output behavior, source-file exclusion, and the alternative tool category. The presence of an output schema covers return structure, so no further return-value explanation is required.

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 0%, so the description must compensate. It enriches both parameters: 'path' means a path to a large, low-density non-source file of specific types, and 'intent' means a specific goal that selects relevant spans. It could add more detail about path formats or intent phrasing, but the semantics are sufficiently conveyed for a simple 2-parameter tool.

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?

Descriptions state a specific verb-driven operation: given a file path and intent, return only relevant verbatim line-numbered spans, never a summary. It clearly defines the resource type (large, low-density non-source files) and the output form, making it easy to distinguish from other tools.

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 says when to use the tool: for large, low-density non-source files such as logs, build output, CSV, JSON, and HTML. It also says when not to use it—source code files—and directs the agent to code-navigation tools instead, providing a clear alternative.

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