cyberchef_corpus_diff

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

Annotations already mark the tool read-only and idempotent, and the description adds substantial behavioral detail on top: it infers structure from byte AND bit variance, reports where repeated blocks sit, and emits the XOR of nonce-reused bodies. This goes well beyond the safety profile provided by annotations.

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 a single dense paragraph with no filler. The core purpose is front-loaded, each subsequent sentence describes a distinct capability, and the closing assumption is a necessary constraint. Every sentence earns its place.

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?

Given the tool's analytical complexity and the absence of an output schema, the description gives high-level but useful output expectations: field groupings, block locations, and an XOR result. It does not specify the exact return shape or how the three analyses are organized in the response, so a small gap remains for an agent that needs to interpret results precisely.

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 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining what the analyses actually do (field grouping, block position reporting, XOR evidence), and it enriches the samples parameter with the fixed-length or left-aligned assumption. It does not tie these details to specific parameter names, but it still adds useful context.

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: 'Compute statistics ACROSS a set of samples.' It then enumerates the concrete analyses performed (field inference, repeated-block detection, nonce reuse), which clearly distinguishes this tool from single-input recipe/bake siblings. The contrast with Fork makes the purpose and scope unmistakable.

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 states when to use this tool instead of a recipe: 'what a recipe cannot express, since Fork runs each branch separately and nothing combines them.' It also provides a key exclusion condition with 'Assumes fixed-length or left-aligned samples,' telling the agent when the tool is not appropriate.

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