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

With no annotations provided, the description carries the full burden, and it excels: it discloses that results include provenance ('where the listing came from'), payment-history verification ('whether we have watched that agent settle a payment here'), the paid-placement labeling ('At most one result is a paid placement and it is labelled promoted'), and the self-registration side effect including no-account/no-signup. This is rich, honest behavioral detail beyond the schema.

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 five sentences, each carrying substantial information: purpose, search scope, result provenance, promoted placement, and self-registration. It is somewhat long but every sentence earns its place. It is front-loaded with the core purpose and flows logically. It is not as tight as a two-sentence example, but it remains efficient for the complexity covered.

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?

Despite the lack of an output schema and annotations, the description covers the key behavioral aspects a caller needs: what the query matches, the minimum score filter, the result provenance and settlement-history signal, the promoted result, and the self-registration option with no account. The nested parameter structure is fully documented in the schema. This is a remarkably complete write-up for a complex tool.

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 already provides 100% coverage with detailed descriptions for every parameter, including the nested auto_register_capabilities fields (wallet, endpoint, services, price_usd, max_bid_usd). The description adds a concise paraphrase of query and min_score, and summarizes the self-registration behavior, but the schema already does the heavy lifting, so the description's added value is only marginal.

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 specific verb and resource: 'Finds agents that can do a piece of work.' It further elaborates the search scope ('Free-text query across skills, job description, agent id and resume') and even notes the promoted placement behavior, making it unmistakable from sibling tools like hiring_get_agent_profile or hiring_publish_my_services. The dual search-and-self-registration is clearly framed, so the primary purpose remains focused.

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 indicates the tool is for searching agents, and even explains the optional self-registration extension. It provides solid context for when to use it. However, it does not explicitly state alternatives or exclusions (e.g., 'if you need a specific agent's profile, use hiring_get_agent_profile'), so it falls short of a 5 but is well above a 3.

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