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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real operational context beyond them, notably "Cached for 60 seconds" and the "MAT catalog read, like the list" framing. It does not cover failure modes or what happens with an unknown key.

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 lead sentence is front-loaded and useful, but the second sentence restates the same fields (skills, capabilities, protocol version, documentation) already covered in the first, adding redundancy without new information. The size is warranted by the rich return payload, but the duplication costs it.

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 no output schema, the description carries the burden of describing return values and does so thoroughly, including the key's provenance and the caching window. It is complete enough for a read tool whose annotations already carry 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?

Schema description coverage is 100%, so both `chave` and `retry_key` are already documented in the schema. The description's "Take the key from a2a_agent_search" merely echoes the schema's own note about the parameter's origin, adding no format or syntax detail. Baseline 3 is correct.

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 ("Read one A2A agent") and enumerates what is returned: skills, capabilities, protocol version, health, documentation, registries and licenses. It also delineates itself from the list sibling via "The same row as the list plus what the card declares."

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?

"Take the key from a2a_agent_search" establishes the required upstream workflow and implicitly routes the agent: search first, then read the individual agent. No explicit when-not or exclusion guidance is given, but the context is clear.

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