Smoke Control Checker: the site's own MCP server — checker, enquiry (enquiry = a human handoff,...
Scored across 6 tools
The tools split cleanly into two clusters: checker_* (decision guide) and enquiry_* (submission flow), and the descriptions make each role legible. However, checker_answer (step-through), checker_start, and checker_tree (end-to-end reasoning) partially overlap since all three navigate the same decision guide, requiring the agent to read descriptions to pick the right one.
There are two recognizable prefixes (checker_ and enquiry_), but the suffix convention is inconsistent: checker_answer/checker_start/checker_tree use varied noun/verb forms while submit_enquiry puts the verb first and enquiry_describe/enquiry_fields are noun-phrase descriptors. Readable, but not a single predictable verb_noun pattern.
Six tools is well-scoped for a checker plus enquiry flow, but checker_tree arguably duplicates the walk-through coverage provided by checker_start and checker_answer, making one tool potentially redundant.
The surface covers the full decision-guide lifecycle (start, step, whole tree) and the enquiry lifecycle (describe, field schema, two-step validated submit with consent). Minor gaps exist, such as no way to check or cancel an enquiry's status after submission, but core workflows are covered.
Given a question id and the chosen option (its choice index), return the next question or the final verdict.
| Name | Required | Description | Default |
|---|---|---|---|
| choice | Yes | ||
| question | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose the key behavior—returning either the next question or a final verdict—but it does not mention whether the flow state is mutated, what happens for invalid choices, or any session/state requirements.
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?
A single, information-dense sentence. The title and description work together without repetition or filler, and the key input/output behavior is front-loaded.
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?
Adequate for a two-parameter tool: it names both inputs and describes the possible return. However, with no output schema and no annotations, it falls short of fully describing the response shape, error behavior, or what the caller should do with the returned next question/final verdict.
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 schema has 0% description coverage, so the description's clarification that `question` is a question id and `choice` is the chosen option's index is essential. It adds meaning beyond the raw property names and types, though it omits details like how to obtain valid question ids or bounds beyond minimum 0.
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 operation: given a question id and a choice index, return the next question or final verdict. This clearly differentiates it from sibling tools like checker_start or checker_tree, which have different roles in the flow.
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?
Usage is implied: use this when a user has answered a question and the flow should advance. However, it does not explicitly state when not to use it, what prerequisites exist (e.g., starting with checker_start), or how it relates to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The first question of the Smoke control checker decision guide.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of explaining behavior, but it only states that the tool is the first question. It does not disclose whether invoking it starts a new session, simply returns the question text, or has any side effects, and gives no indication of how it behaves beyond being a label.
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 clear sentence with no filler or repetition. It front-loads the essential identity of the tool for a zero-parameter operation.
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 tool with no output schema and no annotations, the description is too sparse. It never explains what the first question looks like, what output an agent should expect, or how this step connects to checker_answer and checker_tree, leaving important operational context missing.
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 and the schema is empty, so there is no parameter detail for the description to add. The minimum baseline of 4 applies because the empty schema already fully documents the absence of arguments.
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 title and description clearly identify this as the starting point of the Smoke control checker decision guide and specifically as its first question. This distinguishes it from the checker_answer and checker_tree siblings, though it lacks an explicit verb such as 'asks' or 'returns'.
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 'first question' implies this tool is used to begin the decision guide, but there is no explicit guidance about when to use it versus checker_answer, checker_tree, or the enquiry tools. No alternative tools or exclusion conditions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Every question, option and verdict of the Smoke control checker guide, for reasoning end to end.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It does disclose the content scope: every question, option, and verdict in the guide. However, it does not describe output format, size, pagination, or whether the data is a static snapshot, which leaves some behavioral uncertainty for a tool that likely returns a large complete tree.
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 sentence with no filler. It front-loads the resource and scope, then states the intended reasoning use. Every word earns its place.
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 names the content scope and the intended use case, which is adequate for a parameterless retrieval tool. However, with no output schema and no explicit mention of how the returned tree is structured or how this tool relates to checker_start and checker_answer in the larger flow, an agent may not fully know what to expect.
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 and the schema description coverage is 100%, so the description has no parameter semantics to add. The empty schema is self-explanatory, and the description appropriately focuses on the tool's content rather than parameters.
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 the resource ('Smoke control checker guide') and the full scope ('every question, option and verdict'), making the tool's purpose reasonably clear. The title reinforces that it exposes the whole decision tree. However, it lacks an explicit action verb like 'returns' or 'loads', so the behavior must be inferred from 'for reasoning end to end.'
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 'for reasoning end to end' implies this tool should be used when the agent needs the entire decision tree rather than stepping through it, contrasting with siblings like checker_start and checker_answer. But the description does not explicitly state when to prefer this over those alternatives, so usage guidance remains implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read first. States plainly what submit_enquiry does on Smoke Control Checker: it starts an enquiry with human providers who quote directly. Nothing is bought, ordered or paid; no quote is guaranteed; it is free. Also returns who receives the details, the consent wording, and how the person confirms.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It fully discloses that the tool is non-transactional, free, not a guarantee, and that it returns concrete details such as who receives the enquiry, consent wording, and confirmation method.
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 compact, front-loaded with the most important instruction ('Read first'), and every sentence adds meaningful information. The title also reinforces the core distinction from transaction-oriented sibling tools without redundancy.
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 the tool has no parameters, no output schema, and no annotations, the description is complete: it states what the tool does, what it does not do, and what information it returns. No critical context is missing.
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 nothing for the description to explain. The baseline for zero-parameter tools is 4, and the description appropriately focuses on the tool's output rather than parameters.
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 states a specific purpose: it explains what submit_enquiry does on Smoke Control Checker, including that it starts an enquiry with human providers. It also distinguishes itself from submit_enquiry by explicitly saying nothing is bought, ordered, or paid and that no quote is guaranteed.
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 opening 'Read first' is a clear usage signal: use this tool before acting with submit_enquiry. The description also clarifies what the tool is not (a purchase or guaranteed quote), which helps an agent avoid invoking the wrong sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Every field of the Smoke Control Checker enquiry: key, label, type, whether required, help text and the allowed options where there are any. Pass answers to submit_enquiry keyed by field key.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states what the tool returns—key, label, type, required, help text, and allowed options—and says 'every field,' indicating exhaustiveness. It omits explicit statements about side effects or return format, but for a zero-parameter read-only field listing, these are minor gaps.
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 concise sentences: the first enumerates what the tool exposes, and the second gives cross-tool guidance. There is no redundancy or filler; every word contributes to understanding.
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 simple zero-parameter tool, the description covers the content of the response and the purpose of the returned keys, making it essentially complete. It does not specify the exact return shape (array vs object), but given the absence of parameters, output schema, and nested structures, that omission is acceptable.
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 no parameters to document; the baseline for zero parameters is 4. The description adds meaningful context by explaining how the returned field keys relate to calling submit_enquiry, which aids correct usage of both tools.
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 the resource ('every field of the Smoke Control Checker enquiry') and enumerates the details it exposes (key, label, type, required, help text, options), making its purpose evident. It lacks an explicit verb like 'retrieve' or 'list' but is unmistakable. It also distinguishes itself from submit_enquiry by explaining that answers go there keyed by these field keys.
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 offers a practical usage clue ('Pass answers to submit_enquiry keyed by field key'), implying this tool supplies the keys needed for submission. However, it never explicitly states when to choose this tool over the siblings enquiry_describe or checker_tree, nor does it mention exclusions or prerequisites. The guidance is useful but indirect.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submits an enquiry to Smoke Control Checker — NOT a purchase, NOT a guaranteed quote. Step 1: call with the answers (keyed by field key from enquiry_fields) and consent=true; it validates and returns a summary, the consent line and a confirmation token — show the person the summary and the consent line. Step 2: only if the person agrees, call again with the same answers, consent=true and the confirmation token; the enquiry is then submitted, and the person receives an email with a link they must click before any provider sees it. Consent means the person has read and agreed to: "Send my contact details to up to three stove installers, chosen by Smoke Control Checker, who'll contact me directly. I'll be emailed each firm's name as my details go to it, and can stop any more firms getting them."
| Name | Required | Description | Default |
|---|---|---|---|
| answers | Yes | the person's answers, keyed by field key | |
| consent | Yes | true only when the person has agreed to: Send my contact details to up to three stove installers, chosen by Smoke Control Checker, who'll contact me directly. I'll be emailed each firm's name as my details go to it, and can stop any more firms getting them. | |
| confirmation | No | the confirmation token from step 1, after the person has approved the summary |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does: it discloses that step 1 only validates and returns a summary, consent line and token, that submission requires a second call, that the person must click an emailed link before any provider sees the data, and the exact scope of consent (up to three installers, email notification per firm, opt-out). Nothing about side effects or prerequisites is left to inference.
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 most decision-relevant fact (not a purchase) is front-loaded, and the two steps are sequenced cleanly with the human-in-the-loop instruction attached to step 1. It is long, and the full consent sentence is repeated verbatim from the schema, but that repetition is defensible for a consent artifact.
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 two-step, token-gated, nested-object tool with no output schema and no annotations, the description supplies everything an agent needs: the call sequence, the required inputs per step, what step 1 returns, and the downstream consequence of submitting. No material gap remains.
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 100%, so baseline is 3, but the description adds real meaning: it ties 'answers' to field keys sourced from enquiry_fields, explains that consent=true is the gate for both steps, and explains that 'confirmation' is the step-1 token supplied only after the person approves the summary. The verbatim consent text is duplicated from the schema, which is why this isn't a 5.
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 specific verb and resource ('Submits an enquiry to Smoke Control Checker') and immediately fences off the two most likely misinterpretations ('NOT a purchase, NOT a guaranteed quote'). An agent can distinguish this from enquiry_fields/enquiry_describe/enquiry_describe-style siblings without opening any schema.
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 lays out an explicit two-call protocol with the condition that selects each call: step 1 with answers + consent, then step 2 only 'if the person agrees' with the returned confirmation token. The when-not guidance ('NOT a purchase') and the human-approval gate are stated rather than implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
submit_enquiry1 field changedInput schema / properties / consent / descriptionPrevious value: -"true only when the person has agreed to: Happy for my details to go to a HETAS-registered stove installer, who'll contact me directly."New value: +"true only when the person has agreed to: Send my contact details to up to three stove installers, chosen by Smoke Control Checker, who'll contact me directly. I'll be emailed each firm's name as my details go to it, and can stop any more firms getting them."checker_answerchecker_startchecker_treeenquiry_describeenquiry_fieldssubmit_enquiryCatchment Checker: the site's own MCP server — checker, enquiry (enquiry = a human handoff, not...
Class Q Checker: the site's own MCP server — checker, enquiry (enquiry = a human handoff, not a...
Steel Beam Checker: the site's own MCP server — checker, enquiry (enquiry = a human handoff, not...
HMO Licence Checker: the site's own MCP server — checker, enquiry (enquiry = a human handoff,...
Add one secure layer between your agents and this server.
