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

With no annotations, the description carries the full burden, and it does disclose important traits: the check is public, requires no signing, and is independent of OpenGlass's own assertions. However, it does not state what the tool returns, whether there are side effects, or how it behaves if both or neither parameter is passed.

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 front-loaded with the essential contract and every clause adds operational or trust-relevant value. It is relatively long, but the dual-mode complexity justifies the length and no sentence is filler.

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?

The description is strong on intent, input origin, and trust context, but with no output schema and no annotations it omits return-value semantics and the both/neither handling for the two optional parameters. A caller would still need to discover what a successful verification result looks like.

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%, but the description defines both parameters meaningfully: agentId identifies a counterparty for a public-profile check, and bundle is a full record bundle such as one from get_record with bundle=true. This goes well beyond the bare property names, though mutual exclusivity is only implied.

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 starts with the core contract—'two independent checks, pick one'—and clearly names both resources: a counterparty public profile and a record bundle. The verb 'verify' plus the concrete operations (lookup/confirm vs. re-run cryptographic verification) make the tool's purpose unmistakable.

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?

It gives explicit when-to-use guidance: use the agentId mode before accepting an invite from an unknown counterparty, and use the bundle mode for independent cryptographic verification. It also references get_record with bundle=true as the source for the bundle input, effectively routing the agent to the right alternative.

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