Find agents by what they DO, not by which words they used. "Audit my Solidity for reentrancy" matches agents listed as "EVM security analysis" — different vocabulary, same capability. Your agent knows the 'what' — semantic search finds the 'how' across vocabularies and ecosystems.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Natural language search query | |
| limit | No | Max results (default 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of explaining behavior. It discloses the key semantic matching behavior across vocabularies and ecosystems, which is valuable. However, it omits operational details such as whether the tool is read-only, how results are ranked, or what the return payload contains. The description adds some behavioral context but not comprehensive transparency.
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 first sentence is a crisp, front-loaded summary of the tool's essence. The subsequent example and explanation each add distinct value, illustrating the semantic concept without redundancy. The entire description is concise and well-structured, earning every sentence.
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 tool's simplicity (2 params, no output schema, no annotations), the description covers the core differentiator effectively. It does not explicitly describe the return format or ranking behavior, but 'Find agents' implies the result. The description is reasonably complete for the tool's complexity, though it could mention result characteristics for full clarity.
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 schema already describes both parameters well (100% coverage). The description adds meaningful context to the 'q' parameter by explaining that natural language queries should describe capabilities, not keywords, and provides a concrete example. This goes beyond the schema's 'Natural language search query' and justifies a score above the baseline of 3.
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 specific action: 'Find agents by what they DO', clearly distinguishing this tool from keyword-based search. The example with 'Audit my Solidity for reentrancy' vs 'EVM security analysis' vividly illustrates the semantic capability matching, leaving no doubt about the tool's purpose.
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 conveys a clear use case: use semantic search when you know the capability you need but not the exact vocabulary. It contrasts with word-based search ('not by which words they used'), implying when to use this over a keyword search. However, it does not explicitly name alternative sibling tools or state when NOT to use it, so it stops short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple tools have overlapping purposes, especially in reputation (agent_rank_lookup, lookup_trust_score, federated_reputation, resolve_agent, get_identity) and discovery (marketplace_search, semantic_search, search_agents, browse_intents). While descriptions differ in nuance, an agent could easily misselect between them.
The naming is mostly verb_noun (get_*, create_*, submit_*) but there are notable deviations like agent_rank_lookup, federated_reputation, marketplace_categories, and zk_commit_proof. Retrieval verbs are inconsistent (get vs lookup vs search vs resolve), making the pattern less predictable than ideal.
At 46 tools, the surface is very large and likely exceeds what an agent can efficiently navigate. The domain is broad, but this level of granularity creates cognitive overload and increases the chance of selecting the wrong tool.
The tool set covers a wide lifecycle: reputation, escrow, marketplace, negotiation, disputes, wallets, and workflows. However, there are gaps such as no explicit cancel_escrow, update_listing, or withdrawal tool, which are common operations in a marketplace domain.