Skip to main content
Glama

Rekvira: EU regulation pinpoints for compliance AI

by com.rekvira
OverviewDiscussionsAdmin

Send feedback to the team

submit_feedback

Send feedback about Rekvira to the team that builds it: a bug, a wrong answer, missing data, a missing feature, a workflow idea, or praise. Every item is read by a person. When to offer it: an answer came back empty or wrong; the user corrected you or the result; a workflow was missing a step the user needed; the user repeats a manual step the service could do for them; the user says they need something the service does not do. Offer once, in one sentence; the user's task comes first. Ask first. Show the user what you will send and send it only after they agree. Their own words, and any client, case, company or personal detail, go only with their explicit OK; then set confirmed=true. With authored_by='agent' you may report your own observation of the service (the tool, what you expected, what came back) without asking, as long as it holds none of the user's words or confidential content. Fill kind and what (the task, and what went wrong or what is needed). For a wrong answer add expected and got. Add tool and query for context (the query only with the user's OK), severity, and contact_email only when the user wants a reply. The reply carries a reference id. Tell the user it reached the team; do not promise a reply or a date.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
gotNoFor a wrong answer: what came back instead
kindNoOne of: bug (something failed or errored), wrong_answer (an answer was returned but it was wrong or misleading), missing_data (a document, record or source the user expected is not covered), missing_feature (something the user needs that the service does not do), workflow_idea (a step, sequence or repeated manual task the service could handle), praise (something that worked well and should be kept), other (anything else)
toolNoThe tool the feedback is about, if one (e.g. the tool that answered wrongly); several: comma-separated
whatNoThe task and what went wrong or what is needed (3-2000 characters)
queryNoThe query or arguments that produced it; only with the user's OK
messageNoOlder name for `what`, kept so earlier callers still work; prefer `what`
expectedNoFor a wrong answer: what the right answer or result would have been
severityNolow | normal | high | blocking (blocking: the user cannot do their work)
confirmedNotrue once the user approved sending this; required for authored_by user or agent_drafted
authored_byNouser (their words) | agent_drafted (you wrote it, they approved) | agent (your own observation)
contact_emailNoOnly if the user wants a reply: the address to reply to

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / tool / description
      Previous value: -"The tool the feedback is about, if one (e.g. the tool that answered wrongly)"New value: +"The tool the feedback is about, if one (e.g. the tool that answered wrongly); several: comma-separated"
  2. Changed14 schema fields changed
    • changedInput schema / properties / authored_by / default
      Previous value: -"user"New value: +null
    • changedInput schema / properties / authored_by / description
      Previous value: -"user | agent_drafted; preserve whose words these are"New value: +"user (their words) | agent_drafted (you wrote it, they approved) | agent (your own observation)"
    • addedInput schema / properties / authored_by / enum
      Added value: +[
+  "user",
+  "agent_drafted",
+  "agent"
+]
    • changedInput schema / properties / confirmed / description
      Previous value: -"true only after the user explicitly approved this message"New value: +"true once the user approved sending this; required for authored_by user or agent_drafted"
    • addedInput schema / properties / contact_email
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Only if the user wants a reply: the address to reply to",
+  "title": "Contact Email"
+}
    • addedInput schema / properties / expected
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "For a wrong answer: what the right answer or result would have been",
+  "title": "Expected"
+}
    • addedInput schema / properties / got
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "For a wrong answer: what came back instead",
+  "title": "Got"
+}
    • changedInput schema / properties / kind / description
      Previous value: -"bug | feature_request | friction | praise"New value: +"One of: bug (something failed or errored), wrong_answer (an answer was returned but it was wrong or misleading), missing_data (a document, record or source the user expected is not covered), missing_feature (something the user needs that the service does not do), workflow_idea (a step, sequence or repeated manual task the service could handle), praise (something that worked well and should be kept), other (anything else)"
    • addedInput schema / properties / kind / enum
      Added value: +[
+  "bug",
+  "wrong_answer",
+  "missing_data",
+  "missing_feature",
+  "workflow_idea",
+  "praise",
+  "other"
+]
    • changedInput schema / properties / message / description
      Previous value: -"The explicitly approved feedback (3–2000 characters)"New value: +"Older name for `what`, kept so earlier callers still work; prefer `what`"
    • addedInput schema / properties / query
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "The query or arguments that produced it; only with the user's OK",
+  "title": "Query"
+}
    • addedInput schema / properties / severity
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "low | normal | high | blocking (blocking: the user cannot do their work)",
+  "enum": [
+    "low",
+    "normal",
+    "high",
+    "blocking"
+  ],
+  "title": "Severity"
+}
    • addedInput schema / properties / tool
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "The tool the feedback is about, if one (e.g. the tool that answered wrongly)",
+  "title": "Tool"
+}
    • addedInput schema / properties / what
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "The task and what went wrong or what is needed (3-2000 characters)",
+  "title": "What"
+}
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover safety flags (readOnlyHint=false, openWorldHint=true, destructiveHint=false). The description adds substantial non-annotation behavior: an explicit consent protocol ('ask first', show what will be sent, set confirmed=true only after agreement), authorship rules, and a confidentiality constraint on user words and client/company details.

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?

Front-loaded with purpose, then when-to-use, then consent, then field guidance, then return handling — a logical order with no filler sentences. It is long and paragraph-dense, but each sentence encodes a rule, so nothing is clearly wasted.

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?

With 11 optional parameters, no output schema, and a consent-sensitive workflow, the description carries all the missing load: it explains the required practical inputs (kind, what), the gating confirmed flag, and what the response contains (a reference id) plus what not to promise. An agent has everything needed to call it correctly.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3, but the description adds conditional usage that the schema does not: fill kind and what, add expected/got only for wrong answers, add tool and query only with the user's OK, and use contact_email only when a reply is wanted. It also flags the return behavior but not much about individual field syntax.

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?

The description states a concrete verb and resource ('Send feedback about Rekvira to the team') and enumerates the exact kinds of feedback accepted (bug, wrong answer, missing data, missing feature, workflow idea, praise). No sibling tool does anything similar, so it is trivially distinguishable from the listed tools.

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?

It gives explicit trigger conditions to offer the tool (empty/wrong answer, a user correction, a missing workflow step, a repeated manual step, a need the service cannot meet) and explicitly says to offer it once, in one sentence, with the user's task first. It also names the condition for when consent is not required (authored_by='agent' with no user words or confidential content), which is a genuine when-not rule.

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

All Rekvira: EU regulation pinpoints for compliance AI toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources