Free (50/day per IP). The agent's current credential: principal company, mandate, status (active, suspended, revoked, expired) and signature. Also by key: /v1/agents/by-key?kind=&id=.
| Name | Required | Description | Default |
|---|---|---|---|
| agent | No | Alternative to credential_id: look up active credentials by agent key. | |
| credential_id | No | credential_id returned by kya_register. |
Changes observed during successful MCP inspections.
Input schema / properties / agent / properties / id / descriptionPrevious value: -"0x address for evm; base64url raw Ed25519 public key for web-bot-auth."New value: +"0x address for evm; base64url raw Ed25519 public key for web-bot-auth; eip155:<chainId>:<identityRegistry>:<agentId> for erc8004."Input schema / properties / agent / properties / id / maxLengthPrevious value: -128New value: +160Input schema / properties / agent / properties / kind / descriptionPrevious value: -"evm: an Ethereum-style wallet (EIP-191 signatures). web-bot-auth: an Ed25519 key (RFC 9421 / Web Bot Auth)."New value: +"evm: an Ethereum-style wallet (EIP-191 signatures). web-bot-auth: an Ed25519 key (RFC 9421 / Web Bot Auth). erc8004: an agent registered in an ERC-8004 Identity Registry; its on-chain agentWallet signs."Input schema / properties / agent / properties / kind / enumPrevious value: -[
- "evm",
- "web-bot-auth"
-]New value: +[
+ "evm",
+ "web-bot-auth",
+ "erc8004"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuinely useful operational context beyond the schema: it is free and rate-limited to 50 calls/day per IP, and it enumerates the possible statuses (active, suspended, revoked, expired) that the response can carry.
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?
Two short sentences, front-loaded with cost/rate limit, then the returned fields, then the alternate lookup. Dense and largely waste-free, though the raw '/v1/agents/by-key?kind=&id=' fragment is cryptic shorthand.
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 and two optional parameters, the description carries the return-shape burden and does so by naming the fields and statuses returned. Rate limit and lookup modes are covered; what is missing is explicit routing vs the paid/sibling verify tools.
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% and both parameters (credential_id, agent.kind/id) are fully documented in the schema, including the alternative-to-credential_id relationship. The description adds only the raw key-lookup URL form, which is marginal beyond what the schema already states, so the baseline 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?
It states clearly what the call resolves — an agent's current credential (principal company, mandate, status, signature) — and offers a key-based variant. The verb 'verify' is only implied rather than stated, but the resource and returned fields are specific enough to distinguish it from siblings like kya_check_action or kya_revocations.
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 'Free (50/day per IP)' note implicitly contrasts it with the paid sibling kya_verify_paid, and 'Also by key' hints at the two lookup modes. However, it never says explicitly when to choose this tool over alternatives or what the free-tier precondition means for the caller.
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.