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

Annotations declare readOnlyHint=false and destructiveHint=true; the description adds meaningful behavior beyond that — server-side RSA-4096 public key validation, key ID computation, and the crucial security fact that the private key is already client-side encrypted so the server never sees the password. It does not, however, explain what the destructiveHint actually destroys (e.g., whether it replaces previously uploaded keys).

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?

Front-loaded with the core action, then credentials/security notes, then an access paragraph. There's minor redundancy around the encryption point, but every sentence carries actionable content.

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 4-param, 4-required mutation tool with no output schema, the description covers purpose, auth prerequisites, and the security model. Its gaps are that it doesn't say what the computed key ID is returned as, or what happens to any pre-existing keys on re-upload.

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 real semantic value: it explains that encrypted_private_key is a client-side encrypted envelope for the user's password, which tells the agent the value must be produced before calling rather than raw key material.

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 (upload an encryption keypair for a HITL config) and clarifies the scope of what the server does versus the client (validates the RSA-4096 public key, computes the key ID). It's easily distinguished from siblings like get_hitl_keys, delete_hitl_keys, create_hitl, and update_hitl.

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?

Gives concrete routing guidance: it requires a Proof account, tells the agent to authenticate then retry, and explicitly warns that start_login does NOT unlock this tool — a genuinely useful negative exclusion. It stops short of describing the prerequisite HITL config lifecycle (e.g., that a hitl_id from create_hitl must already exist) or the relationship to add/update key flows.

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