Fetch the full sanitized claim-vs-evidence scorecard for one Hlido-reviewed agent. Returns every claim, verdict, evidence quote, source surface, and (for CLI/API tests) the captured command + exit_code + duration. Schema v1.0. Use this for agent-to-agent pre-flight evaluation.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The agent's Hlido slug (e.g. 'aider', 'gumloop') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description does the heavy lifting. It discloses that the returned scorecard is 'sanitized' and details the exact contents, including captured command/exit_code/duration for CLI/API tests. This gives behavioral context beyond the schema, though it doesn't explicitly state read-only semantics or note any auth/rate-limit considerations.
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 three sentences: the first states the core function, the second enumerates return contents, and the third gives the use case. Every sentence earns its place with no fluff or redundancy, and it is front-loaded with the most important information.
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 no output schema, the description fully explains what the tool returns (every claim, verdict, evidence quote, source surface, and test details) and when to use it. It also notes the schema version. This is complete for a simple single-parameter fetch tool, leaving no critical gaps about return values or purpose.
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 100%, with the slug parameter already described with an example. The description adds minimal parameter-specific detail beyond 'one Hlido-reviewed agent,' which restates the schema. The bar is therefore baseline 3, and the description does not significantly elevate it.
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+resource: 'Fetch the full sanitized claim-vs-evidence scorecard for one Hlido-reviewed agent.' It clearly states what the tool does and distinguishes it from siblings like get_behavioral_trace or verify_claim by focusing on the claim-vs-evidence scorecard.
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 ends with 'Use this for agent-to-agent pre-flight evaluation,' which provides a clear context for when to use the tool. However, it does not explicitly name alternatives or state when not to use it, so it lacks the explicit exclusion seen in top-tier examples.
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 have distinct purposes (trust_check vs get_scorecard vs explain vs verify_claim are clearly layered), but some overlap exists: find_trusted, find_similar_agents, and recommend all return candidate agents with different ranking criteria, and submit_agent vs request_quick_audit both handle unreviewed agents. Descriptions do a good job of cross-referencing to disambiguate, but the sheer number of discovery/query tools creates mild ambiguity.
The naming is predominantly verb_noun (commerce_check, compare_agents, find_trusted, get_scorecard, verify_claim), which is consistent. Minor deviations: 'explain' and 'subscribe' are single verbs without a noun object, and 'intel_query' reverses the pattern (noun_verb). Overall the pattern is recognizable and predictable.
19 tools is on the higher end but justified for a comprehensive agent-review platform covering trust checks, scorecards, discovery, market intelligence, safety scans, and submission workflows. Each tool serves a distinct function in the lifecycle, though a few (subscribe, report_review_issue) are peripheral. Slightly heavy but within reason.
The surface covers the full lifecycle: discovery (find_trusted, find_similar_agents, recommend), evaluation (trust_check, get_scorecard, explain, verify_claim, get_behavioral_trace), safety (scan_mcp, get_incidents), market intelligence (market_pulse, intel_query), and onboarding (submit_agent, request_quick_audit, report_review_issue). No obvious dead ends; unreviewed agents are handled with clear escalation paths.
