Skip to main content
Glama
semlayer MCP server

semlayer MCP server

review_questions

Read-onlyIdempotent

List open review questions in the loaded semantic layer to surface what is uncertain or unreviewed. Scope by table and limit results, then answer each question to record a verdict.

Instructions

List the open review questions in the loaded layer.

    What is uncertain in this layer, as questions you can answer. Pull
    this when the user asks what is unreviewed or unreliable. Do
    NOT walk the user through it after inference: the questions that
    matter are the ones an answer rested on, and `run_sql` hands you
    those as `assumptions`.

    tables: comma-separated, to scope it to what you are looking at.
    limit: the most to return; `truncated` says whether there were more.

    Read-only. Each question carries its `key`, the claim, what the
    engine saw, and who may decide it. `review_question` gives one in
    full, `review_answer` records a verdict, and `review_decisions` lists
    the ones already given.
    

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "review_questions"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoThe most questions to return. `truncated` in the result says whether there were more.
tablesNoTable names, comma-separated, to list only the questions that touch them. Omit for the whole layer.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.1
    • addedInput schema / properties / limit / description
      Added value: +"The most questions to return. `truncated` in the result says whether there were more."
    • addedInput schema / properties / tables / description
      Added value: +"Table names, comma-separated, to list only the questions that touch them. Omit for the whole layer."
  2. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, and 'Read-only.' merely restates them. However, the description adds genuine value beyond the annotations: it names the per-question payload (key, claim, what the engine saw, who may decide), explains that `truncated` signals more results exist, and warns against a specific downstream misuse pattern. Minor redundancy keeps it from a 5.

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?

Purpose and trigger are front-loaded, and every block (trigger, exclusion, params, return contents, siblings) carries distinct information. It is denser and more conversational than needed, and the parameter lines repeat the schema, but there is no filler sentence.

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?

For a two-parameter read tool with full schema coverage, annotations, and an output schema, this covers trigger, exclusions, scoping, and sibling routing adequately. The only gap is that 'open' is never contrasted with the decided set beyond the pointer to review_decisions, and result ordering is unstated—both minor given the output schema is present.

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 coverage is 100% and both parameter descriptions already explain `tables` and `limit` including the `truncated` signal, so the description's parameter lines are essentially restatements. The only slight addition is the framing 'to scope it to what you are looking at,' which does not add syntax or behavioral detail beyond the schema, so the baseline 3 applies.

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?

Opens with a specific verb+resource+scope: 'List the open review questions in the loaded layer,' then clarifies the semantics as 'What is uncertain in this layer, as questions you can answer.' This distinguishes it cleanly from review_question (one in full), review_answer (record a verdict), and review_decisions (already-decided ones).

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?

Gives an explicit trigger ('Pull this when the user asks what is unreviewed or unreliable') and an explicit exclusion with an alternative ('Do NOT walk the user through it after inference ... `run_sql` hands you those as `assumptions`'). It also routes to the three sibling review tools by function, leaving nothing to inference.

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