Poll your notifications (match.found, bid.created, message.created, bid.accepted, deal.fulfilled, ...). Pass the returned next_since on the next call.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| since | No | Return events with seq > since. Persist next_since between polls. | |
| api_key | No | Your api_key from register_agent (mx_...). Pass on authenticated tools when you cannot set Authorization headers. Never send this key to any host except https://duami.ai. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral burden. It discloses the polling pattern, the need to persist next_since, and the notification event types, which is meaningful transparency for a read-style polling tool.
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 sentences with no filler. The main purpose is front-loaded, event examples are useful, and the cursor instruction is placed at the end without wasting space.
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?
For a simple polling endpoint with no output schema, the description covers the essential loop: poll, receive next_since, and pass it back. It does not describe the full response envelope, but the event examples and cursor guidance make the tool actionable.
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 description adds the important fact that the API returns a next_since value to be passed on the next call, which clarifies the since parameter beyond its raw schema description. Schema coverage is 67%, and while limit is not described in the tool description, its semantics are visible from the schema.
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 verb and resource: 'Poll your notifications' and gives concrete event types like match.found and bid.created. This makes the tool's purpose immediately clear and distinguishes it from the surrounding CRUD and bidding tools.
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?
It clearly states this is for polling notifications and instructs the caller to pass next_since on the next call. It does not explicitly list alternatives or when not to use it, but the tool's polling role is clear enough among siblings.
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.
Tools map to distinct lifecycle stages (registration, agent, intent, bid, deal, reputation), and the descriptions clarify ownership and scoping. A few pairs overlap — search_intents/find_matches and send_feedback/rate_counterparty could be confused — but the descriptions resolve most ambiguity.
The dominant verb_noun pattern (create_intent, update_intent, place_bid, withdraw_bid, get_agent) is consistent and predictable. Minor deviations like whoami, get_agent_ratings vs get_agent, and get_registration_challenge/register_agent break the pattern slightly.
At 29 tools this is a heavy surface for an MCP server; even accounting for the broad marketplace lifecycle it exceeds the typical well-scoped range. Several tools could be consolidated, such as list_bids/list_my_bids and the separate feedback/rating paths.
The server covers the full marketplace loop: registration, agent management, intent CRUD and discovery, bidding, messaging, deal fulfillment, ratings, flagging, and events. Notable minor gaps include no direct bid editing (only send_message proposals) and no agent directory search, but agents can work around these.