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

Resolves the otherwise confusing annotation profile: a Q&A tool marked readOnlyHint=false is explained by "may probe the agents involved and record health results," which names the exact side effect. It also bounds the side effects explicitly ("cannot change, suspend or delist anyone"), matching destructiveHint=false and telling the agent what is safe to ask. This is precisely the behavioral context annotations cannot convey.

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-loaded with the core action and scope, then capabilities, then the hard limit, then the conversation continuation rule. Every sentence carries distinct information and none restates the name or schema fields.

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?

An output schema exists, so return values need no explanation; annotations cover open-world and idempotency semantics. What remains — what the tool can and cannot do, whether it has side effects, and how to maintain conversation state — is all covered.

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 0%, so the description must carry the parameters. It explains conversation_id functionally as a continuation handle, which is real meaning beyond the schema's bare "Conversation Id" title with null default. The question parameter is largely self-evident, though "in natural language (any language)" usefully widens the expected input format.

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 ("Ask the ONAA Registry Steward a question in natural language") and enumerates the question domains it covers: listing status, agent health, A2A compatibility, incidents, flag reasons, network status. That is far more informative than the name alone. It does not explicitly name a sibling such as get_listing or verify_attestations, so the boundary is implied by the free-form orchestrator framing rather than stated.

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 clear usage context: use it for natural-language diagnostic questions spanning multiple check types, in any language. It also tells the caller how to continue a thread ("Pass the same conversation_id to continue a conversation"). It stops short of stating when to prefer a narrower sibling getter instead, so agents must infer the boundary.

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