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

Annotations declare write, non-idempotent, non-destructive behavior, so the safety profile is covered structurally. The description adds genuinely non-obvious context the annotations cannot: the key must be created externally and only the public address submitted, and retries should reuse the same agentId. It omits what happens on an agentId collision and any authorization requirements beyond 'signed-in profile'.

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?

Five short, front-loaded sentences with the purpose first and no filler. The telegraphic 'Default: signed-in account. Optional separate account and controls.' is compact but slightly clipped, and 'import an agent' is never explained, which costs a point.

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 an output schema present, return values need not be explained, and 100% schema coverage handles the 23 parameters. The description supplies the missing operational framing (external key custody, reuse of agentId) for what is clearly a multi-step provisioning call. Only conflict/error behavior on an existing agentId is left unaddressed.

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% across 23 parameters, so the schema already documents chain, preset, wallet, delegation, and spend fields in detail. The description largely restates the agentWallet semantics ('omit to use the signed-in profile') and the key-handling rule that the schema also states, adding little semantics beyond it. Baseline 3 applies when the schema carries the load.

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 or import an agent on your profile' — so an agent immediately knows this is provisioning, not linking or mounting. It does not name or contrast with siblings like proofable_agent_link or proofable_agent_mount, so the boundary between 'create' and 'link/mount' must be inferred.

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 operative guidance: default to the signed-in account, optionally use a separate account and controls, generate/retain the key outside Proofable and pass only the public address, and reuse the same agentId on retries. It stops short of explicit when-to-use-this-instead-of-a-sibling routing or any exclusions.

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