Create a new agent team for multi-agent trust scoring. Owner is auto-added as first member. Note: for production use, prefer the REST API (POST /api/v1/teams) which requires wallet signature verification.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Team name (max 100 characters) | |
| description | No | Team description (max 500 characters) | |
| wallet_address | Yes | Wallet address of the team owner (must be a registered agent) |
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 burden. It discloses that the owner is auto-added as first member, a behavioral trait. However, it does not mention auth requirements (beyond the REST API note), error conditions, or return values, leaving gaps. The production note is more of a recommendation than a behavior, so the actual behavioral disclosure is limited.
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 two sentences, front-loads the purpose, and provides a useful side note about the owner and a production alternative without any fluff. Every sentence earns its place.
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?
The tool has no output schema, and the description does not explain return values or error behavior, but it covers purpose, a key side effect (owner auto-added), and a usage recommendation. This is reasonably complete for a simple create operation, though it could mention response details for full completeness.
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 schema covers 100% of parameters with descriptions. The description adds the note that the owner is auto-added, which provides slight context to the wallet_address parameter (i.e., the owner need not be listed as a member), but it doesn't significantly go beyond the schema. Baseline 3 is appropriate given high schema coverage.
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 uses a specific verb ('Create') and resource ('agent team') and adds context ('for multi-agent trust scoring'), clearly distinguishing it from sibling tools like team_trust_check or browse_agents. It fully states what the tool does with no ambiguity.
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 description explicitly states that for production use, the REST API (POST /api/v1/teams) is preferred because it requires wallet signature verification. This provides a clear alternative and when-to-use guidance, which is exactly what a good usage guideline should do.
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.
Several tools overlap in purpose, such as bridge_erc8004_lookup and bridge_erc8004_trust_check, trust_check, get_agent, and get_agent_reputation all returning trust or reputation data. Descriptions help clarify the distinctions, but the similarities could lead an agent to select the wrong tool.
Naming uses a mix of conventions: verb-noun (get_agent, search_agents), noun-first (compliance_report, dns_discovery), and prefix-based groupings (trust_*, bridge_*). While snake_case is consistent, the inconsistent verb/noun ordering and synonyms (lookup, check, verify) make it less predictable.
With 19 tools, the set is slightly heavy but still justified by the platform's broad feature set covering trust checks, reputation, teams, wishes, compliance, and credentials. Some tools could be merged (e.g., bridge_erc8004_lookup and bridge_erc8004_trust_check), but the count is not excessive for the apparent scope.
The tool surface focuses heavily on reading and checking trust data, but lacks obvious lifecycle operations such as updating or deleting agents, creating wishes, or managing endorsements. The presence of create_team without corresponding team management (update/delete) leaves a notable gap.
