Skip to main content
Glama
Aidress-ai
by Aidress-ai

call_agent

Send a request to a registered agent through the Aidress proxy, providing agent ID, payload, and caller ID, and obtain a response with a transaction ID.

Instructions

Send a request to a registered agent through the Aidress proxy.

All calls are logged. Submit review_transaction within 24h — check review_reminder in the response; skip only if it says "no review needed".

agent_id — the agent to call. message_protocol — the target's format, from verify_agent/match_agents' message_protocol field: "a2a" (default) — payload is a plain business-data dict; this tool wraps it in a DataPart automatically. "mcp" — payload IS a complete MCP JSON-RPC message, sent verbatim. Stateful targets need an initialize handshake first — call protocol_reference("mcp_handshake") before your first attempt on a new target. "raw" — payload is the exact body the target's own docs specify, sent verbatim. Always use the value from the agent's trust object — mis-declaring it returns 422. mcp_session_id — session token from a prior initialize call. Only for message_protocol="mcp"; see protocol_reference("mcp_handshake"). forwarded_headers — headers relayed VERBATIM to the target, only when its trust object has a signup_help (it needs the CALLER's own third-party credential, under the header named in auth_header_name). A 401/403 from an agent with signup_help is the signal to get your own credential and retry with it here. Reserved headers (X-Payment, Mcp-Session-Id, Host, Content-*) are ignored. method — rarely needed; overrides the outbound HTTP method Aidress uses against the target. See protocol_reference("call_agent_advanced_fields"). payload — business data (message_protocol="a2a") or the exact protocol message (message_protocol="mcp"/"raw"). Check payload_schema on the agent first — mismatched currency/units/date format returns 409. caller_agent_id — REQUIRED: your agent's ID. Must match your set agent key or /call rejects the request (401 missing/invalid key, 403 mismatch). No anonymous calls. x_payment — Leave UNSET in normal use — only for a pre-signed x402 PaymentPayload (V2) if you're driving your own wallet manually. On a 402 without x_payment, the result carries a payment.pay_via proxy URL instead — see the server's payment-flow instructions (shown at session start) for how to use it. SKIP THE 402 ENTIRELY: if verify_agent/match_agents already returned this agent's routing.price_schedule + routing.pay_via, sign a PaymentPayload yourself for the matching task's declared price and pass it here as x_payment on your FIRST call — no discovery round-trip.

Auth (REQUIRED): on the hosted remote connector, your own Authorization: Bearer header on the MCP connection is used automatically. Locally: set AIDRESS_AGENT_KEY env var, call set_agent_key(...) once in-session, or configure AIDRESS_KEYPAIR_PATH. Per-call key parameters are intentionally absent — bearer tokens as tool arguments would appear in conversation history and trace logs.

Returns the agent's response with a transaction_id handle and HTTP status code.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
methodNo
payloadYes
agent_idYes
x_paymentNo
mcp_session_idNo
caller_agent_idYes
message_protocolNo
forwarded_headersNo
Behavior5/5

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

With no annotations provided, the description fully bears the transparency burden. It discloses that all calls are logged, requires review_transaction within 24h, describes error codes (401/403, 409, 422, 402), explains auth mechanisms (bearer token, env var, set_agent_key), and reveals that per-call key parameters are intentionally absent to avoid trace leakage. It also explains the 402 payment flow in detail. This is exemplary behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but justified given the tool's complexity (8 parameters, multiple protocols, auth, payment flow). It is front-loaded with the core purpose and then logically groups parameter details. Some sentences are dense and could be restructured (e.g., splitting the x_payment block), but nothing is redundant. It earns its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers all necessary context for a high-complexity tool: return value (transaction_id and HTTP status), error conditions, auth setup, follow-up review requirement, and payment handling. Even without an output schema or annotations, an agent can fully understand invocation, side effects, and expected outcomes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds rich meaning to every parameter beyond the bare schema. For example, message_protocol gets an entire block explaining each enum value and its payload implications; mcp_session_id is scoped to mcp protocol; forwarded_headers describes verbatim relay and reserved-header exclusions; x_payment gets a detailed payment-flow explanation. Even though the schema has 0% coverage, the description fully compensates, making each parameter's semantics crystal clear.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Send a request to a registered agent through the Aidress proxy.' This clearly distinguishes call_agent from siblings like verify_agent/match_agents (which provide agent metadata) and review_transaction (which handles post-call review). The scope is explicit and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives extensive when-to-use guidance: it explains how to obtain message_protocol from verify_agent/match_agents, when to use protocol_reference for MCP handshakes, when to call review_transaction (with a skip condition), and when to set x_payment. It also states that anonymous calls are not allowed, clarifying a key limitation. This far exceeds basic usage guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Aidress-ai/Aidress'

If you have feedback or need assistance with the MCP directory API, please join our Discord server