A2A: Request

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description aligns with this by stating 'Writes are DISABLED: only the read-only methods are offered.' It adds behavioral context about the raw reply format (protobuf JSON, Part as {'text':'...'}, state as 'TASK_STATE_SUBMITTED') and that the endpoint comes from the peer's agent card. This goes beyond annotations and is accurate.

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 dense but highly informative, front-loading the purpose and key warnings. Every sentence adds value, covering the escape-hatch nature, usage boundaries, raw reply format, endpoint source, and write restrictions. It is appropriately structured for a complex tool.

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?

Given the tool's complexity (3 params, nested objects, raw protocol exposure) and no output schema, the description fully covers what an agent needs: method naming, param formats, response shape, and authorization constraints. It even mentions the environment variable for write access and the lack of shaping, making it complete for correct invocation.

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?

Although the input schema provides 100% coverage, the description enriches each parameter: for url it clarifies it's the base URL not the card path historical naming; for method it details v1.0 vs 0.x naming conventions and error codes; for params it gives concrete examples and explains camelCase fields. This adds significant value beyond the schema.

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 identifies the tool as an escape hatch for direct A2A JSON-RPC calls, explicitly contrasting it with typed tools that shape responses. It specifies the verb 'call' and the resource (A2A JSON-RPC method), and distinguishes it from siblings by noting it returns raw unshaped replies.

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 explicitly states when to use this tool ('only for something the typed tools do not cover') and contrasts with typed tools that shape responses. It also explains that the endpoint is derived from the peer's agent card, preventing arbitrary URLs, and notes that writes are disabled with an environment variable to enable them. This gives clear usage boundaries and alternatives.

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