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

Annotations only declare it is a non-read-only, non-destructive local write; the description adds two facts annotations cannot carry — the required auth headers and that the api_key is displayed only once. That one-time-secret warning is genuinely useful behavior disclosure. It stops short of describing uniqueness constraints or error behavior.

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 tight sentences with the action first, the auth prerequisite second, and the return-value caveat last. Zero filler.

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 mutation tool with annotations and no output schema, the auth and one-time-key facts cover the riskiest gaps. But with 0% parameter coverage and no output schema, the description should explain the four inputs — especially 'template' and 'capabilities' — to be complete.

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% across 4 parameters, so the description carries the full burden — and it says nothing about name, price, template, or capabilities. An agent cannot tell what 'template' refers to, whether name must be unique, or what capability strings are valid, all of which matter before calling.

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?

Specific verb and resource: 'Register a new agent', plus the notable outcome that an api_key is returned once. It does not explicitly contrast with siblings like discover_agents, but the create-vs-list distinction is inferable from the name alone.

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 description surfaces a hard prerequisite (X-Owner-Token and X-PoW headers on the /mcp request), which is real usage guidance for an agent that would otherwise fail. However, it names no alternatives and gives no when-not-to-use condition beyond that implicit auth gate.

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