Free top-of-funnel scan: could a buyer agent find and buy this publisher? Checks adagents.json, standardized taxonomy tagging, audience segments in a readable schema, and a product/deals catalog. Returns what a buyer agent would see and what it cannot.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Publisher domain, for example example.com. | |
| outputFormat | No | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. States it checks specific data sources and returns what a buyer sees and what it cannot. Does not disclose side effects (likely read-only), authorization requirements, rate limits, or cost beyond 'Free'. Adequate but not detailed.
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, front-loaded with purpose and scope. Every word adds value. No fluff.
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 low complexity (2 parameters, no nested objects, no output schema), description sufficiently covers what the tool does and returns. Mentions specific checks and output characteristics. Minor gap: no mention of prerequisites like domain validity or format details beyond example.
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 50% (only domain has description). Description does not elaborate on parameters beyond schema; it adds context about the output but not parameter meaning. Baseline 3 is appropriate; description does not compensate for the missing outputFormat description.
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?
Clearly states the tool performs an audit to determine if a buyer agent can find and buy a publisher. Lists specific checks (adagents.json, taxonomy, segments, catalog) and describes output. Distinguishes from siblings like run_publisher_revenue_audit by focusing on buyer readiness.
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?
Labels it as a 'Free top-of-funnel scan' implying it's a preliminary check, but provides no explicit guidance on when to use versus alternatives like run_publisher_revenue_audit or check_crawler_blocks. No exclusions or when-not-to-use advice.
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.
Many tools are clearly scoped (e.g., `create_sulvo_ad_unit` vs `delete_sulvo_ad_unit`), but there is confusion with tools like `run_publisher_revenue_audit` and `get_publisher_revenue_audit_checklist` which sound like they could overlap. Also, `start_sulvo_signup` and `create_sulvo_signup_account` seem to operate on different stages of signup but could be confused at a glance.
The naming convention is generally consistent with a `verb_sulvo_noun` pattern (e.g., `create_sulvo_ad_unit`, `delete_sulvo_ad_unit`). The `get_` and `run_` prefixes are used somewhat inconsistently (e.g., `run_publisher_revenue_audit` vs `get_publisher_revenue_audit_checklist`), and some tool names feel a bit verbose, but overall patterns are recognizable.
With 40 tools, the server covers a massive surface area including signup, activation, reporting, and auditing. While each tool has a specific purpose, the number feels somewhat bloated for a single server, suggesting it could be split into more focused sub-servers (e.g., `sulvo-signup`, `sulvo-reporting`). It is on the high end of 'appropriate'.
The tool set appears very complete for the Sulvo ecosystem, covering everything from account creation (`create_sulvo_signup_account`) to auditing (`run_agentic_readiness_audit`) and activation (`submit_sulvo_activation_workspace`). The only minor gap is the lack of a direct way to start signup beyond step 1, but this is documented as an API limitation, not a tool gap.
