A2A: Discover Agent

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

Annotations declare readOnlyHint=true, and the description does not contradict that—the tool only fetches and caches, no mutation. The description adds valuable context: it always refetches, making it the live check for peer status, and it caches the card locally (implying a state change). This is more than just restating the read-only nature; it discloses the caching side-effect and the staleness risk, which is helpful.

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?

The description is two sentences, each carrying weight. The first sentence states the core purpose and the always-refetch behavior alerts to staleness. The second provides actionable guidance on when to use and what it enables. No fluff, well front-loaded.

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?

The tool is simple with one parameter, and the description covers the purpose, usage timing, and behavioral nuance (cache, staleness). No output schema exists, but the description mentions it returns skills and transports. No nested objects or enums to worry about. It feels complete for an agent to call correctly.

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% (the single `url` parameter is described), but the description adds crucial meaning: it clarifies that the URL should be the base URL, not the card path, and that the client appends the well-known suffix. Also, it tells the agent to obtain the URL from a2a_list_agentscacheList. This is exactly the kind of parameter meaning that the schema alone does not fully convey.

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 the action (fetch a peer's agent card), the resource (the well-known endpoint), and the purpose (return skills and transports). It also distinguishes itself from siblings by emphasizing the 'always refetches' behavior, which positions it as the tool for checking peer availability and capabilities, different from a2a_list_agents.

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?

Explicitly instructs to use this tool before a2a_send_message to an unfamiliar peer, and explains why (to discover the correct binding, URL, and skills). It also indicates this is a way to check if a peer is up and current, with the caveat about staleness. While it doesn't explicitly mention alternatives or when not to use, the context is clear and direct.

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