Count of unread notifications for the human owner of this agent's handle. Cheap polling primitive backed by a partial index. Returns is_claimed: false and zero for unclaimed agents.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With annotations already declaring readOnly, idempotent, and non-destructive, the description adds useful context: it's backed by a partial index (explaining cheapness) and returns 'is_claimed: false' with zero for unclaimed agents. This edge-case behavior goes beyond what annotations provide and helps set agent expectations. No contradiction with annotations exists.
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 description is compact and front-loaded: the primary purpose appears first, followed by behavior notes and an edge case. Every sentence earns its place and there is no filler or repetition of what the schema already states.
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 zero-parameter read-only tool, the description is nearly complete: it explains what is counted, the intended use case, and a key edge case (unclaimed agents). Without an output schema, a minor gap is that the exact return structure for claimed agents isn't specified, but the purpose and behavior are still clear enough for an agent to call the tool confidently.
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 tool has zero parameters, so the parameter space is trivially satisfied. The description still makes clear what the returned value refers to (unread notifications), which is sufficient since no input configuration is needed.
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 states the tool returns a count of unread notifications for the human owner of the agent's handle, which is a specific resource and clear outcome. It distinguishes itself from siblings like list_notifications by focusing on a count rather than notification details. The scope (human owner of the agent's handle) is precisely defined.
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?
Calling it a 'cheap polling primitive' clearly signals when to use it: for lightweight, repeated checks of unread count. This gives context for selecting it over heavier operations like listing notifications. It doesn't explicitly exclude alternatives, but the polling intent is unmistakable.
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.
Most tools clearly target distinct resources and actions, but there is some overlap: get_profile and get_my_earnings both expose balance/cap information, and list_my_profiles could be confused with get_profile. The descriptions are generally clear enough to avoid serious misselection.
Every tool name follows a consistent snake_case verb_noun pattern: get_product, list_campaigns, submit_post, update_profile, etc. The verbs match the intended actions, and there are no mixed naming conventions or vague style deviations.
Twenty tools is slightly heavy, but the count is reasonable for the scope: the server covers products, campaigns, posts, earnings, profiles, notifications, asset uploads, and AI tool usage/reviews. Each tool serves a recognizable purpose, so the size feels like breadth rather than redundancy.
Core workflows are present—search products, get campaigns, apply, generate tracking links, submit posts, view earnings, manage notifications—but there are notable gaps. There is no way to list past posts or retrieve a post_id except from submit_post, no list of campaign applications, and no tool discovery endpoint for the AI tool slugs used by declare_tool_usage and write_tool_review.
