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

Goes well beyond the annotations by disclosing the critical side effect: the response carries an edit token and 4-word recovery phrase shown ONCE, exposed in the conversation, and must be stored immediately. It also surfaces the per-address daily listing cap and the content restriction on texts — exactly the behavioral context an agent cannot infer from readOnlyHint/destructiveHint/idempotentHint.

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-loads the purpose, then flags the one-time credential warning in caps where it will be seen, then tacks on limits. Dense but every sentence earns its place; the trailing 'Same rules as POST /register' is slightly opaque since it references an external endpoint the agent may not know.

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 no output schema, the description explains the essential return payload (edit token + recovery phrase) and the rate limit. Remaining gaps — whether the card publishes immediately, failure behavior, and the image moderation flow — are minor given annotations already cover the safety profile.

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?

With only 30% schema coverage across 10 parameters, the description carries much of the load by naming name, specialty, description, endpoints, protocols, tags, country, and capabilities, and by clarifying the endpoints object keys (a2a, mcp, api, site). It omits image and built_with, and adds no format details for maxLength-constrained fields, so it is strong but not fully compensating.

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 a card for an agent') and enumerates the fields it accepts, making it clearly distinguishable from get_agent, search_agents, and update_agent. An agent knows immediately this is the creation path.

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 useful operating context ('Free, instant, no account', 20 listings/day per address, no commands in texts) but never states when to prefer this over update_agent or what to do if the agent already exists. Usage is implied by the create semantics rather than explicitly guided.

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