checker_answerGiven 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 |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the happy-path return value but does not disclose whether calling it records an answer, advances state, is idempotent, or how invalid question/choice values are handled. This leaves an agent uncertain about side effects.
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 focused sentence with no filler. It front-loads the inputs and clearly states the output, making it easy for an agent to parse quickly.
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 core input/output contract is present, but there is no output schema and no description of the structure of the 'next question' or 'final verdict'. It also does not mention that the question id and choice options likely come from checker_start, leaving some flow 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?
Schema description coverage is 0%, and the description compensates by explaining that `question` is a question id and `choice` is the chosen option's index. This adds meaning beyond the raw schema, though it does not specify the source or valid range of the question id.
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 the operation: given a question id and a choice index, return the next question or final verdict. This distinguishes it from siblings like checker_start or checker_tree. A minor ambiguity is that the schema parameter is named 'question' rather than 'question_id', which slightly weakens precision.
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 context is implied: it must be called after a question is presented, since it returns the 'next' question. However, there is no explicit guidance about when to use this tool versus checker_start, checker_tree, or other siblings, and no exclusions or prerequisites are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The checker_* tools are clearly separated from the enquiry_* tools, and each has a distinct role: start, traverse, or view the full decision tree. However, checker_answer and checker_tree could be confused by an agent looking to answer a single question, since both expose question/option/verdict data.
The checker_ and enquiry_ prefixes provide a useful grouping, but the individual names mix conventions: checker_start and checker_tree are noun-like, checker_answer and enquiry_describe are noun-verb, enquiry_fields is noun-noun, and submit_enquiry is verb-noun. The pattern is readable but not consistently applied.
Six tools is a well-scoped count for a server covering two related workflows: the HMO licence decision guide and the enquiry submission flow. Each tool has a clear purpose and none feel redundant or excessive.
The decision guide is fully covered with start, step-by-step traversal, and full-tree reasoning, enabling both interactive and end-to-end use. The enquiry flow is also complete: context, schema, validation, consent, and two-step submission are all represented.