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

With no annotations, the description carries the behavioral burden. It discloses the auth prerequisite, implies a first-call failure if unauthenticated by saying 'then call this tool again,' and documents the returned key material. It could add a note that the keypair is sensitive, but the read-only nature is clear from 'Get' and 'Returns.'

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 tight: one sentence for purpose and return value, one short block for access. Every sentence earns its place, including the caveat about start_login.

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?

For a one-parameter read tool with no output schema, the description supplies the return shape and the prerequisite auth flow. There is no obvious missing information that would prevent an agent from invoking it correctly.

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% and the single parameter hitl_id is documented as 'HITL config ID.' The description adds no deeper meaning beyond the schema, but none is really needed for a single, well-named parameter.

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 uses a specific verb and resource: 'Get the encryption keypair for a HITL config,' and states the exact return fields (public key, encrypted private key, KDF salt, key ID). This clearly separates it from related HITL siblings like upload_hitl_keys or delete_hitl_keys.

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 gives clear conditions for calling: a Proof account is required, the client must be authenticated first, and the tool should be called again after authentication. It also warns that start_login does not open this tool. It stops short of explicitly comparing with alternatives such as upload_hitl_keys, but the access guidance is actionable.

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