Create public key

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

Annotations already declare readOnlyHint=false and destructiveHint=false, which align with the add operation. The description adds only that it's for SSH keys. It doesn't disclose side effects like duplicate key handling, response structure, or whether the key is account-wide. Given the non-destructive nature indicated by annotations, the lack of additional behavioral detail is acceptable but not enhanced.

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?

Two concise sentences, with the primary action front-loaded. No redundant information. The second sentence adds relevant context (SSH keys for VPS) but could be integrated into the first. Overall efficient and easy to parse.

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 create operation with no output schema, the description doesn't explain what a successful response looks like (e.g., key ID, status) or any error conditions. It also doesn't clarify whether keys are account-scoped or need to be attached separately. Given the tool's simplicity, the core purpose is covered, but an agent would benefit from knowing the expected outcome and usage flow.

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 descriptions are purely tautological ('key parameter', 'name parameter'), providing no meaning. The description hints that 'key' is an SSH key but doesn't specify format (e.g., RSA, Ed25519), required encoding, or how 'name' should be used. Since the schema itself is unhelpful, the description fails to compensate, leaving the agent uncertain about parameter expectations.

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 clearly states 'Add a new public key to your account' – a specific verb and resource. It adds context by specifying 'SSH keys for VPS authentication,' which helps differentiate from attachment operations like VPS_attachPublicKeyV1. However, it doesn't explicitly contrast with the attach tool.

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?

The second sentence says 'Use this endpoint to register SSH keys for VPS authentication' – more of a purpose than usage guidance. It provides no conditions for when to use this over VPS_attachPublicKeyV1 (which presumably attaches keys to a VM), no exclusions, and no prerequisites. The agent is left to infer the appropriate context.

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