key.derive

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

With no annotations, the description carries the full burden of explaining side effects, but it only mentions inputs, processing steps, and return values. It does not state whether the operation is read-only, whether file paths are read, or whether any state is modified.

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 compact and uses a clear process arrow, with no redundant filler. However, the density of domain-specific terms makes it harder to parse, slightly reducing accessibility.

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 mentions several outputs but leaves crucial context unexplained, such as what 'stamped κ' refers to, what 'prior' means, and how 'glyphs', 'lit vertices', and 'walked vertices' are defined. There is no output schema to fill these gaps.

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 description for 'key' is detailed and useful, specifying accepted formats: JSON object, JSON string, sigil PNG as base64/data URL, or a path. This goes beyond basic type information and gives practical input guidance.

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 conveys a derivation-and-comparison process, but it is heavily jargon-laden and does not clearly define key terms such as 'stamped κ', 'prior', or 'lit and walked vertices'. The purpose is inferable but not directly stated in plain language.

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?

No explicit guidance is given about when to use this tool versus sibling tools like key_verify, key_evolve, or compare_plain. The 'never trusted, only re-derived' rule hints at a principle, but it does not specify concrete use cases or selection criteria.

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