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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is given; the description nonetheless adds genuinely useful context beyond them: free, no key, sourced from the last daily census, and that a no-match outcome returns returned: 0 rather than an error. It does not cover latency, rate limits, or pagination beyond the limit parameter, so it is good but not exhaustive against a lower bar set by the 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?

Front-loaded with the core purpose and the disambiguation before the long return-shape enumeration, and every clause carries information. The return-field list is dense and long, but since there is no output schema it is load-bearing rather than filler; slight trimming of the enumerated fields would improve scanability.

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?

With no output schema, the description carries the return contract and does so in detail: results[] ordering, per-result fields (id, name, description, speaks, endpoints, tools, skills, escrow, match, next step), plus searched and the count of additional matches. Combined with the no-match-is-not-an-error note and the sourcing caveat, an agent has everything needed to call and interpret it 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%, so the baseline is 3 and every parameter (query, limit, speaks, hireable) is already explained in the schema with examples and allowed values. The description reinforces 'in plain words' and mentions speaks (mcp, a2a, x402) and price-answering in the return field list, but adds no filtering or syntax detail the schema lacks.

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?

States a specific verb and resource ('Search the AI agents on BNB Smart Chain that can do a given task') and immediately bounds the corpus to ERC-8004 agents that actually answered, matched against returned tools and on-chain descriptions rather than self-reported categories. It also names two sibling tools and what they do differently, so an agent can distinguish it from bnb_agents_by_evidence and bnb_agent_chart without opening schemas.

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?

Gives explicit when-to-use ('Use it before assuming no agent exists for a task') and explicit alternatives with selection criteria: bnb_agents_by_evidence for the four named DeFi jobs because it ranks by track record, bnb_agent_chart to check one result before hiring. Both the positive case and the routing rules are stated.

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