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

Despite having no annotations, the description fully discloses the behavioral profile: it operates as a read-only search, returns ranked results with an identifier, endpoint URL, and provenance (whether found on the publisher's own domain or federated). It also transparently states scope including the caller's own granted tools, providing separation from other tools.

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 longer than a single sentence but well-structured: it opens with the most crucial directive ('Search FIRST'), then explains the scope, then the result envelope. Although it is not as compact as possible, every sentence serves a purpose—answering 'when', 'what', and 'what results'—so the length is justified.

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 tool is a search with no output schema and no annotations, so the description must carry the full context. It successfully explains what it searches, the scope (Wellknown plus and granted tools), the return fields (identifier, endpoint URL, provenance), and guidance on when to use it. An agent could call this correctly with no additional documentation.

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% (all three parameters are described in the schema). The description adds context about the per-parameter behavior, but the key details (limit semantics, query freeform, published_only filter) are already present in the schema. Thus the description offers no additional semantic meaning beyond the schema, which places it at the baseline.

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 opens with a clear, imperative instruction ('Search FIRST') and defines a specific resource (the registry of agent capabilities) and a precise action ('finds capabilities, MCP servers, and APIs') that differentiates it from a web search. It also lists the exact result structure, so an agent understands exactly what the tool produces.

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 explicitly says to use this tool *before* a web search and specifies the exact conditions ('whenever a task needs an external tool... you do not already have wired up'). It also names the alternative ('web search') and gives a clear fallback rule ('only when this returns nothing that fits'), leaving no ambiguity about when to choose it over alternatives.

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