diff

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

With no annotations, the description carries the full burden and does so thoroughly: it explains content-based line-by-line diffing for structured formats, byte-level change detection for binary formats, and the meaning of full=false. It also discloses the binary=true marker behavior without any contradiction.

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 dense sentences cover scope, file-type routing, comparison modes, and flag semantics with zero filler. The main purpose is front-loaded, followed by structured technical details.

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 no annotations, the description provides enough behavioral detail for an agent to invoke diff correctly: input requirements, file-category behavior, and the effect of the only optional parameter. The presence of an output schema covers return-value expectations.

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 0%, so the description compensates by explaining the full parameter's behavior explicitly. It identifies dir_a and dir_b as the two unpacked directories, though it does not clarify comparison direction/order semantics, which is a minor gap.

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 states a precise verb and resource: compare two unpacked directories object-by-object. It enumerates the file types and comparison modes, so the tool's role is unmistakable and clearly distinguished from sibling tools like unpack/repack.

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 makes clear this tool operates on two unpacked directories (the result of unpack), giving strong context for when to call it. It does not explicitly name alternatives or exclusions, but the usage context is unambiguous enough for agent selection.

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