raw

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

No annotations are provided, so the description carries the full burden. It only states it is a passthrough and gives an example, but lacks details on side effects, authorization, rate limits, or error behavior, leaving significant behavioral gaps.

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 extremely concise, consisting of one sentence and an example. Every element is purposeful: the purpose, migration hint, and usage example are front-loaded and efficient, with no wasted words.

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?

As a legacy wrapper, the description covers basic usage and migration, but it omits what the tool returns (e.g., the result of the wrapped tool) and error handling. Given the tool's simplicity, this is adequate but could be more complete for someone unfamiliar with the pattern.

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 schema describes 'tool' as a string and 'args' as an object with additional properties. The description adds a concrete example ('raw({ tool: "view_file", args: { path: "..." } })'), which clarifies the expected structure and usage of the arguments, adding value 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?

The description clearly states it is a 'Legacy tool passthrough' and provides an example call. It distinguishes itself from the sibling tool 'cmd' by recommending its use instead, making the purpose and differentiation explicit.

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 advises using 'cmd()' instead, providing a clear alternative. However, it does not specify conditions under which 'raw' might still be necessary or any prerequisites, slightly limiting guidance.

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