inspect_file

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

Annotations already cover read-only, idempotent, open-world, and non-destructive behavior. The description adds useful behavioral context beyond that: it is a cheap metadata probe, returns estimated token cost, and is intended to prevent context-window blowout. It does not detail URL auth or size limits, but the added cost/decision context is substantial.

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 purpose is front-loaded in the first phrase, and the second sentence gives the operational rule and rationale. It is dense but every clause earns its place by clarifying output, cost, or usage.

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?

Covers what it returns, why it should be used before full reads, and how it helps select slices. With full schema coverage and rich annotations, the only missing details are minor (e.g., URL auth), and the description is complete enough for an agent to call it correctly.

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 the schema already documents the path/url/data mutually exclusive modes and the optional mimeType hint. The description mentions the three input modes but adds no syntax, format, or precedence details beyond what the schema provides. Baseline 3 is appropriate.

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 action (cheap probe) and resource (file via path/url/base64), and lists the metadata it returns. It clearly distinguishes itself from the read_* sibling tools, which perform full content reads, by positioning itself as the pre-flight inspection step.

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?

Explicitly says to ALWAYS call this first on anything larger than a few KB, and explains the decision it enables: choosing which read_* tool and which slice to request. This is strong when-to-use guidance tied directly to sibling selection.

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