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

Annotations already establish the read-only, idempotent, open-world, and non-destructive nature. The description adds value by disclosing behavioral traits beyond annotations: results are ranked, a total count is included for pagination, and semantic search is optional (query vs. precomputed embedding). No contradiction with annotations.

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?

One well-crafted sentence carries the purpose, key filters, and output summary. Every clause earns its place and no informational filler is present. The description is front-loaded with the action and resource.

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 the output schema exists and the input schema covers all parameters, the description provides the necessary high-level orientation: what the tool searches on and what it returns (ranked matches and total count). An agent has enough context to select and invoke the tool correctly.

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 100%, and the schema already documents every parameter with constraints and semantics (e.g., limit, offset, sort_by, min_reputation, include_unreachable). The description adds no new meaning beyond naming capability, minimum reputation, and semantic search, so the baseline of 3 applies.

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 leads with a specific verb ('Find') and a resource ('agents'), then names the core filter dimensions (capability, minimum reputation, semantic search) and the return shape (ranked matches plus total count). This clearly distinguishes discover_agents from sibling tools like hire_and_execute, register, or find_paid_work.

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 clearly implies when to use the tool—when an agent needs to search or discover agents by filters or semantic relevance. However, it does not explicitly state when not to use it, nor does it reference alternative tools (e.g., get_recommended_action or find_paid_work). The context is clear but not exclusionary.

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