Skip to main content
Glama
Sign In
Wicked MCP server

Wicked MCP server

by WickedAPI
OverviewSchemaSourceRelated ServersDiscussions(1)Admin
TypeScript
Hybrid

sanity_check

Verify a single claim before acting by checking it against supplied source text or live web evidence, returning a verdict and confidence score so you can support, reject, or treat it as unverified.

Instructions

[Wicked Sanity] Verify one claim before acting on it. Verdicts: supported | contradicted | unsupported | insufficient_evidence (see data). confidence_score is raw consistency (a "contradicted" verdict scores near 0). Policy: act on supported; treat unsupported/insufficient_evidence as unverified; reject contradicted. x402 or SANITY_API_KEY; 429 means a rate limit — see retry_after.

Use when you must verify one claim before acting on it, either against source text you supply or against live web evidence. Not for many claims at once (use sanity_check_batch).

Behavior: writes state upstream (not read-only); needs the credentials or wallet signature noted above where applicable.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "claim": "<claim>"
    },
    "name": "sanity_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo"grounded" (default; check against context) or "open" (check against live web evidence — consistency with the web, not objective truth).
claimYesThe single statement to verify (max 5,000 chars).
contextNoSource text the claim(s) must be faithful to. Required for mode "grounded".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds useful context beyond the annotations: credential requirements (x402 or SANITY_API_KEY), upstream state writes, and 429/retry_after rate-limit behavior, all consistent with readOnlyHint=false and openWorldHint=true. However, much of the space is spent restating the verdict vocabulary and confidence semantics, and it does not explain what state is written upstream or what a failure other than a 429 looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence front-loads purpose, verdicts, and policy efficiently, but the 'Use when you must verify one claim before acting on it' line repeats the first sentence almost verbatim, and the trailing 'Behavior:' sentence partly duplicates the credential and non-read-only points already made.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by naming the verdict values, the `data` field, and confidence_score semantics, plus retry_after on rate limits. Combined with the auth note and the grounded/open evidence framing, an agent has everything needed to call it and interpret the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already explains mode (grounded/open), claim length, and the context requirement for grounded mode. The description adds only an indirect gloss ('source text you supply or against live web evidence') that restates the schema without new syntax or formatting detail, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Verify one claim'), enumerates the possible verdicts, and explicitly names the sibling it is not (sanity_check_batch) for the multi-claim case. An agent can distinguish this from sanity_check_batch and sanity_get_check without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger ('Use when you must verify one claim before acting on it'), names the two supported evidence sources, and names the alternative tool with the condition that selects it ('Not for many claims at once — use sanity_check_batch'). It also supplies an action policy per verdict, which is genuine decision guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools