Skip to main content
Glama
Verinoda-Labs

Verinoda

by Verinoda-Labs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

analyze

Answers repository questions with verifiable claims, file:line evidence, test observations, and re-indexes if the tree changes.

Instructions

Answer a question as claims with evidence: one verdict per sub-question, claims with file:line, unknowns with next steps, and the passages. needs_clarification is a normal result (ask the user). run_tests / observe also run or trace the tests that reach the answer (isolated copy). Re-indexes first if the tree changed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionYesThe question.
budget_secondsNoWall-time budget in seconds (1-600).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.4.0
    • removedInput schema / properties / budget_calls
      Removed value: -{
-  "default": 40,
-  "description": "Internal tool-call budget (1-200).",
-  "type": "integer"
-}
    • removedInput schema / properties / observe
      Removed value: -{
-  "default": false,
-  "description": "Trace the tests that reach the answer with the runtime call tracer (isolated copy) and attach what they observed.",
-  "type": "boolean"
-}
    • removedInput schema / properties / plan_json
      Removed value: -{
-  "default": "",
-  "description": "A checked question plan as JSON text (from `verinoda plan check`); used instead of drafting one.",
-  "type": "string"
-}
    • removedInput schema / properties / question / default
      Removed value: -""
    • changedInput schema / properties / question / description
      Previous value: -"The question to answer with claims and evidence (optional when plan_json is given: the plan's user_message is used)."New value: +"The question."
    • removedInput schema / properties / run_tests
      Removed value: -{
-  "default": false,
-  "description": "Also run the tests that statically reach the answer (isolated copy, allowlisted runners only).",
-  "type": "boolean"
-}
    • addedInput schema / required
      Added value: +[
+  "question"
+]
  2. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, and the description explains why: it re-indexes first if the tree changed. It also discloses that test runs/traces happen on an isolated copy and that needs_clarification can be a legitimate result. That is meaningful behavioral context beyond the annotation flags, though the side effects of re-indexing are not fully spelled out.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first clause, which is good, but the remaining text is a dense run-on mixing result format, clarification behavior, test execution, and re-indexing. Phrases like 'run_tests / observe also run or trace the tests' are cryptic and cost the reader clarity.

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?

With no output schema, the description must carry the return contract, and it does: verdicts, claims with file:line, unknowns with next steps, passages, plus clarification and test behavior. For a complex analysis tool this is fairly complete, though side-effect and failure-mode detail remains thin.

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% with two parameters (question, budget_seconds), so the schema already documents both. The description adds no syntax, format, or budget-interaction detail beyond what the schema provides, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb+resource: it answers a question and returns verdicts, claims with file:line, unknowns with next steps, and passages. That is far more concrete than the bare name 'analyze' suggests. However, it never names or contrasts with the siblings (project_query, code_check), so an agent cannot cleanly route between them from this text alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied (pose a question, expect claims/evidence) and it usefully notes that needs_clarification is a normal outcome to escalate to the user, plus the budget parameter exists. But there is no explicit when-to-use vs. when-not, no prerequisites, and no routing guidance against project_query or code_check, leaving selection to inference.

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

Deploy Server

Other Tools