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

With no annotations, the description carries the full behavioral burden. It usefully discloses the signal shape and an interpretive caveat ("evidence for consumer policy, not a universal trust score"), which is real added value. But it omits read-only/auth requirements, ordering, truncation, and whether results are paginated or scoped to one agent.

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?

Two tight sentences: usage condition first, returned payload second, with the interpretive caveat packed into the same sentence. No filler or repetition of the name/title.

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 a one-parameter read tool with no output schema and no annotations, the description is a reasonable minimum: it explains intent and response contents. It is still incomplete on the parameter format, safety profile, and result limits, which nothing else in the definition supplies.

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% and the single required "agent" parameter is undocumented in both places. The description mentions an agent's "identity" but never states the accepted identifier form (handle, DID, numeric id), which is exactly the gap low schema coverage should have been compensated for.

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 makes clear that the tool returns per-signal evidence (category, state, source, observation time) for an agent, which is enough for an agent to understand the resource. However, it never explicitly names the retrieval verb or distinguishes the output from near-siblings like get_agent, verify_agent, and inspect_agent_passport, which all surface agent trust/identity data.

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?

"Use when evaluating an agent's identity, capability, or registry evidence" gives a concrete decision context with a clear intent (consumer policy evaluation). It stops short of naming alternatives or exclusions — an agent still has to guess whether to call this, verify_agent, or inspect_agent_passport first.

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