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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's added value is real: it discloses the 60s cache window, the retry_key idempotency window, that data is unfiltered/unreviewed and served live from public registries, and that the call is forwarded to a MAT catalog index host. It stops short of describing auth requirements for the private api_pass or rate limits.

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 purpose and filter logic are front-loaded and earn their place, but sentences like 'no review queue hides a record; quality is the order, never visibility' and 'which travels with the data' are promotional filler that a calling agent gains nothing from. Trimming those would make it tighter without losing any operational meaning.

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 an 11-parameter, no-required, read-only search tool with no output schema, the description supplies the row shape (merge across registries, `fontes`, `creditos`, `key` for a2a_agent) and the combination semantics. It omits only return-count/pagination framing, though the schema's `_links.next` hint covers that adequately.

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%, so baseline is 3, but the description adds cross-parameter semantics the schema does not: values within one parameter are OR'd while different parameters are AND'd. That is genuinely useful combination logic beyond per-field docs, and the per-field meanings are left correctly to 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 first sentence names a specific verb (Find) plus the resource (A2A agents, defined as agents publishing an AgentCard) and enumerates the searchable axes: text, health, protocol version, registry, skill tag, publisher. It also implicitly separates itself from the sibling a2a_agent by stating each row carries that tool's key, so an agent can tell the search tool from the fetch tool.

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 implies the workflow (search here, then use the `key` with a2a_agent) and states the OR/AND filter semantics and 60s cache, which guide how to call it. But it never explicitly says when to prefer this over siblings like mcp_index_search or feed_search, nor any conditions to avoid it. Usage is inferable rather than stated.

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