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 does disclose that the result is a challenge to sign, implying a non-mutating read, but says nothing about whether the DID must already be registered, whether the challenge expires, single-use semantics, or error behavior for unknown DIDs. 'Crossed once' is unexplained.

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?

It is a single compact sentence, which is appropriate, but the phrasing is cryptic rather than efficient — 'crossed once' consumes space without informing. The core action is not front-loaded in plain language.

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?

With no annotations, no output schema, and 0% schema coverage, the description must supply everything, yet it omits prerequisites (must the DID be enrolled?), the challenge's lifetime, and what the caller does with the returned challenge. Only the DID formats and the nature of the return are covered.

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 0%, so the description must compensate, and it does add real value by naming the accepted formats ('did:key or did:web') for the otherwise bare 'did' string parameter. However, it gives no format syntax examples or constraints, so the compensation is partial.

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 name 'haven_key_challenge' is only restated in metaphor ('a did:key or did:web that crossed once gets a challenge to sign'). The verb is implied rather than stated — the agent must infer that it submits a DID and receives a signing challenge. The phrase 'crossed once' is opaque jargon that doesn't clarify the operation or distinguish it from haven_key_enter/haven_verify.

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?

'Return with your key' hints at an authentication flow, but there is no explicit statement of when to call this versus siblings like haven_key_enter, haven_verify, or haven_gate, nor any prerequisite or sequencing guidance. The agent is left to guess where this step sits in the auth flow.

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