Evidence-backed trust verdict for an agent service before you transact. Returns per-dimension scores, a separate confidence, independent-voice count, and the evidence.
| Name | Required | Description | Default |
|---|---|---|---|
| subject | Yes | Service URL, numeric id, or @agenty-handle. | |
| min_evidence_tier | No | 1 identity · 2 receipt · 3 reproduced. | |
| min_reviewer_karma | No | ||
| max_staleness_hours | No | ||
| require_human_linked | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavior disclosure. It lists return elements (per-dimension scores, confidence, independent-voice count, evidence) which gives some insight into behavior, but it does not mention whether the operation is read-only, what side effects exist, or any rate limits or dependencies. This is adequate but not richly transparent.
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, then a compact list of return values. Every word earns its place; there is no redundancy or filler.
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 description provides a solid overview of purpose and outputs, but lacks parameter explanations, usage alternatives, and behavioral notes. Given no output schema or annotations, the description is minimally adequate but leaves significant gaps for an agent to use the tool effectively.
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 description coverage is low (40%) with only 'subject' and 'min_evidence_tier' described. The description does not compensate for the other parameters (min_reviewer_karma, max_staleness_hours, require_human_linked) and adds no parameter-specific meaning beyond 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 states a specific verb+resource: 'Evidence-backed trust verdict for an agent service before you transact.' It clearly explains what the tool does (returns a verdict) and distinguishes itself from siblings (get_service, search_services) by focusing on trust assessment rather than service discovery or details.
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 phrase 'before you transact' provides clear usage context, implying you should call this to assess trust before a transaction. However, it does not explicitly state when not to use this tool or name alternatives, so it falls short of fully explicit guidelines.
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.
get_service and get_verdict both return verdicts with evidence, differing only in lookup (numeric id vs. unspecified). An agent could easily confuse which one to use, especially since get_verdict does not specify its input. search_services is distinct.
All tool names follow a consistent verb_noun pattern: get_service, get_verdict, search_services. Both 'get' verbs are for retrieval and 'search' for discovery, making the naming uniform and predictable.
3 tools is within the ideal 3-15 range for a focused service. Each tool serves a clear role in retrieving verdict data or searching the directory, with no redundancy in count.
For a read-only service, the surface covers search and retrieval of verdicts and evidence. The only minor gap is that get_verdict and get_service are redundant, and there is no explicit 'list all' but search covers that. No major lifecycle gaps exist.