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

Annotations already declare readOnly/idempotent/harmless, and the description adds non-obvious behavior: results are relevance-ordered, and verification does not certify legal identity or trustworthy performance. This caveat is valuable because it prevents an agent from over-trusting 'verified' results.

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 compact and front-loaded with purpose. The filter sentence partly overlaps with the first sentence's list of search facets, but each sentence adds functional information and the caveat earns its place.

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?

Given 9 parameters and no output schema, the description explains the core use and filtering but omits pagination behavior, query semantics, and result shape. It is sufficient for a basic call but not complete for advanced parameter usage.

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?

The input schema has zero descriptions, so the description must carry semantics. It maps well to protocol, evidenceLevel, verifiedDomain, verifiedBuilder, and skill/domain, but says nothing about limit, offset, or query, and names only MCP/A2A without mentioning the API protocol enum value. Coverage is partial.

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 uses a specific verb ('Discover'), names the exact resource ('public AI agents'), and identifies the source index ('indexed by Remnant'). It also clearly separates this tool from the sibling memory/passport/agent-inspection tools by focusing on discovery and filtering.

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 concrete usage context: search and filter by skill, domain, protocol, evidence level, verified domain, and Builder relationship. It does not explicitly name alternatives or exclusions, but the discovery context is clear enough for an agent to select this over inspect_agent or memory tools.

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