create_key

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

With no annotations, the description carries the full behavioral burden. 'In the TEE' hints that key material is generated inside a trusted execution environment, but there is no mention of required permissions, whether the secret material is ever returned, whether the operation is idempotent, or what the response contains.

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?

Three short sentences, no waste, and the core action and its main variation (key types, curve rules) are front-loaded. Nothing is padded or restated.

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?

It covers key-type and curve semantics well, but with no annotations and no output schema it says nothing about authorization requirements or what a successful creation returns (e.g. a key handle/ID), which an agent needs before calling a creation tool.

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 baseline is 3, but the description adds a real cross-parameter constraint the schema does not encode: secret keys accept only ed25519, whereas the schema enum alone would suggest either curve is valid for any non-mnemonic type.

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 verb and resource ('Create a new key in the TEE') and enumerates the three supported key types. It implicitly separates itself from import_key (creates rather than imports) but never names the sibling it must be distinguished from, so differentiation is left to inference.

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?

It explains the constraint that curve is required for private/secret but omitted for mnemonic, which is useful conditional guidance. However, it never says when to choose this tool over import_key or keygen, nor when each key type is appropriate, so alternatives are unaddressed.

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