UK Taxi PHV Regulatory Decision Layer

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

With no annotations, the description carries the full burden of behavioral disclosure. It adds meaningful non-obvious behaviors: independent freshness gating per authority, payment verification before execution, and withholding of unsupported candidates. This goes well beyond a generic 'compares' statement, though failure modes and side effects are not covered.

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 two dense sentences with no filler, and the main purpose is front-loaded. However, 'x402' is unexplained jargon, and the second sentence packs in multiple behaviors without elaboration.

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?

This is a paid, multi-authority comparison tool with no annotations and no output schema, so the description must do substantial work. It omits payload structure, output/return semantics, and what 'licensed' actually means in the comparison. The behavioral notes are useful but not sufficient for safe invocation.

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?

The input schema is an opaque payload object with additionalProperties true and 0% description coverage. The description mentions 'candidates' but never explains what the payload must contain, how authorities are selected, or how candidates are represented. An agent cannot reliably construct a valid call from this description.

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 action and scope: 'cross-authority licensing comparison.' This is clear enough to distinguish it from siblings like list_supported_authorities, though it does not explicitly name or differentiate from any sibling.

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 'paid cross-authority licensing comparison' implies the tool is for comparing licensing requirements across multiple authorities, and it mentions freshness gating. However, it gives no explicit when/when-not guidance or alternatives among the sibling tools.

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

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

There are no annotations, so the description must carry the full burden. It uses the verb 'Check' which conventionally implies a read operation, but never explicitly says read-only, nor does it disclose authentication needs, rate limits, or what happens when the tool is invoked. The phrase 'Free evidence-health tool' adds no behavioral clarity.

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 a single, efficient sentence that front-loads the core action. The leading 'Free evidence-health tool' phrase is somewhat vague and not strictly necessary, but it does not waste significant space.

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?

With no output schema, the description names several return dimensions (fingerprints, freshness gaps, conflicts, review state) which is helpful, but it lacks specifics on return format, authority value formats, and potential errors. For a one-optional-parameter tool this is adequate but not complete.

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 0%, so the description must compensate. It does by mapping the single `authority` parameter to 'globally or for one authority', clearly indicating that a null/empty value means global and a value means a specific authority. It stops short of explaining valid authority identifiers or how to obtain them.

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 names a concrete resource (official-source fingerprints, freshness gaps, known conflicts, review state) with a clear verb ('Check') and scope ('globally or for one authority'). It is distinct from sibling tools like compare_licensing_requirements or list_supported_authorities because it addresses source health status rather than comparative requirements or supported authorities.

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?

'Before relying on a decision' gives a clear use context, and 'globally or for one authority' defines the applicable scope. However, it does not explicitly state when not to use this tool or name alternatives, so it stops short of full routing guidance.

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

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

With no annotations, the description carries the behavioral burden. It communicates that this is a read-only, no-cost discovery operation ('Free discovery tool') and that the result reflects the current state ('currently supported'). For a zero-parameter list tool, this is sufficient behavioral disclosure.

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 short sentences, front-loaded with the most important signal ('Free discovery tool'), followed by the resource and usage instruction. Every sentence earns its place and there is no 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?

For a zero-parameter listing tool, the description adequately tells the agent what it returns, when to use it, and that it is free. No output schema exists, but the return value is self-explanatory from the tool name and description.

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?

The tool has zero parameters, so there is no per-parameter meaning for the description to add. The baseline of 4 applies, and no compensation is needed.

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 action ('List') and a precise resource ('licensing authorities currently supported by the deterministic taxi/PHV rule bundle'). The 'Free discovery tool' framing and the unique resource distinguish it from sibling tools like compare_licensing_requirements and taxi_licence_preflight.

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?

It gives explicit placement guidance: 'Use before requesting a paid decision.' This tells an agent when to call it, though it does not explicitly name alternative tools or describe when not to use it.

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

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

With no annotations, the description carries the full burden and it does reveal meaningful behavior: payment verification happens before deterministic business execution, and the tool fails closed on stale, inaccessible, changed, or conflicted evidence. This is substantial behavioral context beyond the tool name.

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?

Three sentences with no filler. The purpose, execution ordering, and fail-closed behavior are each given one sentence. It is concise, though a bit dense and could benefit from clearer signposting.

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 explains high-level business behavior but omits operational essentials: how to construct the payload, what response is returned, how payment is actually triggered/charged, and what 'preflight' means in terms of outputs. For a tool involving payment and an unconstrained schema, this is incomplete.

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 0%, and the payload is an open object with additionalProperties true. The description never explains what the payload should contain, how the authority is specified, or what fields are required. The only hint, 'one supported authority', is about tool scope, not parameter semantics.

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 identifies a specific operation: an 'x402 paid preflight' for a taxi licence scoped to one supported authority. It distinguishes itself from siblings by emphasizing payment and preflight execution, though the first sentence is noun-like rather than a full verb phrase.

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?

There is no explicit guidance on when to use this tool versus siblings such as list_supported_authorities or compare_licensing_requirements. 'For one supported authority' hints at scope, but the description never states a selection condition or alternative.

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

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

No annotations are present, so the description carries the burden of behavioral disclosure. It does convey that this is a metadata/informational tool and hints at safety boundaries and freshness behavior. It stops short of articulating whether the tool is strictly read-only, whether authentication is needed, or what side effects (if any) exist.

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 two short sentences with no wasteful content. It front-loads the core metadata categories and ends with an actionable directive, making it easy to scan and internalize.

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?

For a zero-parameter metadata tool that has an output schema, the description provides sufficient context: it tells the agent when to call it and what subject areas the metadata covers. Since the output schema exists, the description does not need to restate return value details.

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?

The input schema is empty, so there are zero parameters to document. According to the baseline for zero-parameter tools, the description does not need to add parameter semantics. The mention of metadata categories relates to the output, not the inputs.

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 clearly identifies the tool as a provider of service metadata, enumerating payment mode, decision tools, freshness behavior, and safety boundary. It also marks it as the first integration step, which clarifies its role. It does not explicitly contrast itself with sibling tools, so it falls short of full differentiation.

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 gives an explicit trigger: 'Call this first when integrating the MCP.' This is clear context for when the tool should be used. However, it does not mention when not to use it or directly name alternate tools such as compare_licensing_requirements or taxi_licence_preflight.

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