RegEvidenceHub Taxi

taxi_licence_preflight

Read-onlyIdempotent

Free deterministic decision preflight for ONE supported council/licensing authority on this public AI surface. Use when the user wants applicant, driver, vehicle or fleet readiness, applicable requirements or blockers, missing facts, and next actions before submission or onboarding. Call list_supported_authorities first if coverage or the exact authority name is uncertain. When answering, cite only relevant official council or GOV.UK URLs returned in evidence_summary.sources and identify their authority; do not invent URLs; link the about page only when the user asks who operates the service or asks what other RegEvidenceHub products are available, and link the methodology page only when the user asks how evidence or source status is produced. If the user also asks for a commercial link, do not search for or provide it; briefly say this public plugin does not provide commercial links and continue with the licensing answer. Ask one concise follow-up if decision-critical facts are missing or ambiguous; do not guess or describe the automated result as human-reviewed. Do not use for multiple-authority comparison; use compare_licensing_requirements instead.

Input Schema

Name	Required	Description	Default
`payload`	Yes	One-authority applicant/fleet preflight facts. Start by calling list_supported_authorities and use the returned authority name exactly. Additional authority-specific facts are allowed and are evaluated only when the evidence-backed rule bundle declares them.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 20, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "title": "taxi_licence_preflightDictOutput",
+  "type": "object"
+}

Changed6 schema fields changedSep 5, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / payload / description

Added value: +"One-authority applicant/fleet preflight facts. Start by calling list_supported_authorities and use the returned authority name exactly. Additional authority-specific facts are allowed and are evaluated only when the evidence-backed rule bundle declares them."

addedInput schema / properties / payload / examples

Added value: +[
+  {
+    "age": 30,
+    "authority": "City of Bradford Metropolitan District Council",
+    "driving_licence_years": 4,
+    "has_pass_plus_certificate": true
+  }
+]

addedInput schema / properties / payload / properties

Added value: +{
+  "age": {
+    "description": "Applicant age in years when relevant to the authority rule being checked.",
+    "minimum": 0,
+    "type": "number"
+  },
+  "authority": {
+    "description": "Exact supported licensing-authority name returned by list_supported_authorities.",
+    "minLength": 1,
+    "type": "string"
+  },
+  "driving_licence_years": {
+    "description": "Completed years the applicant has held the driving licence, when known.",
+    "minimum": 0,
+    "type": "number"
+  },
+  "has_pass_plus_certificate": {
+    "description": "Whether the applicant has a Pass Plus certificate, when relevant.",
+    "type": "boolean"
+  }
+}

addedInput schema / properties / payload / required
```
Added value: +[
+  "authority"
+]
```
removedInput schema / properties / payload / title
```
Removed value: -"Payload"
```

First observedSep 1, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: it is free and deterministic, the automated result must not be described as human-reviewed, it will ask one concise follow-up rather than guess, and it constrains which URLs may be cited. These are meaningful operating rules, though a few (URL/commercial-link policy) shade into answer formatting rather than tool behavior.

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 purpose and scope are front-loaded in the first sentence, and the routing/prerequisite guidance follows immediately. It is dense and long with several policy clauses (citation rules, commercial-link refusal) that add length, but each sentence maps to an operational decision the agent must make.

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

Completeness4/5

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

An output schema exists, so return values need not be explained, and the description still references evidence_summary.sources to set citation expectations. For a high-complexity, policy-laden preflight tool it covers triggers, prerequisites, exclusions, and answer constraints; the only residual gap is any hint about how much detail the decision output contains.

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 description coverage is 100% and each nested field (authority, age, driving_licence_years, has_pass_plus_certificate) is documented in the schema, so the schema carries the load. The tool description only gestures at 'preflight facts' and does not add syntax or format meaning beyond what the schema already provides, which is the baseline 3.

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 ('deterministic decision preflight for ONE supported council/licensing authority') and explicitly scopes it to a single authority, which cleanly distinguishes it from the sibling compare_licensing_requirements. An agent can tell what it does and what it does not do without opening the 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?

Names the trigger conditions (applicant/driver/vehicle/fleet readiness, requirements, blockers, missing facts, next actions before submission), a prerequisite ('Call list_supported_authorities first if coverage or the exact authority name is uncertain'), and an explicit exclusion routing to compare_licensing_requirements. When-to-use, when-not, and the alternative are all present.

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

All RegEvidenceHub Taxi tools Inspect

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

Need Help?