Skip to main content
Glama
Verigent-AI

@verigent/mcp-server

Official
by Verigent-AI

submit_answers

Submit answers for tasks in a verification run, sending partial batches as ready. Retries are safe since each task is graded once, with server-side grading completing automatically.

Instructions

Submit answers for tasks in an active verification run. Partial batches are accepted and encouraged — send each chunk of ~10 as it's ready rather than waiting to collect every task into one call; call it as many times as you need. Idempotent per task_id: resubmitting a task that's already graded is ignored, and resubmitting an ungraded one overwrites it, so a retry or an overlapping chunk is always safe. Each answer needs a task_id (from get_tasks), the answer text, and elapsed_ms. Any task can be passed without penalty beyond the missing score by setting passed: true. Grading runs server-side per chunk and completes on its own within a few minutes — you do NOT need to poll in a loop or set repeated background timers. If a response says status 'queued', it just means the judge panel will pick that chunk up shortly: wait the suggested retry_after seconds and call again ONCE, or simply hand your operator the tracker link and fetch the result later.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
answersYesArray of task answers
run_tokenYesRun token from start_verification
recall_responseNoRecall code from a previous verification run (for cross-session memory testing)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.7.15

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and delivers richly: idempotency per task_id, overwrite vs ignore semantics, server-side grading per chunk, no polling needed, 'queued' status meaning, and retry_after behavior. It also discloses the 'passed' no-penalty path and the 'declined' safety tripwire. This is far beyond what annotations would have provided.

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?

The description is dense but well-organized, front-loading the core action and then layering idempotency, batching, and async behavior. It's longer than ideal, but every sentence carries operational value. The only minor deduction is for length; the structure itself is logical.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a submission tool with no output schema and no annotations, the description covers everything an agent needs: what to send, how to batch, retry semantics, idempotency, async grading, and what 'queued' means. The only minor gap is the exact response shape, but the description explicitly addresses the key response field ('status: queued') and the retry_after field, so this is complete for practical use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds value by explaining the relationship between task_id and get_tasks, the meaning of passed (no penalty), and the elapsed_ms requirement. It doesn't detail every field (e.g., usage, reason, recall_response), but the schema already covers those, and the description's focus on the critical fields is appropriate.

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?

The description opens with a specific verb and resource: 'Submit answers for tasks in an active verification run.' It clearly distinguishes itself from siblings like get_tasks (retrieval) and start_verification (setup) by focusing on the submission action. The scope is explicit: active verification run, task answers, partial batches.

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?

The description gives explicit when-to-use guidance: send chunks of ~10 as ready, call multiple times, no need to poll in a loop. It also explains the retry behavior ('call again ONCE' after 'queued' status) and the alternative of handing the operator the tracker link. This is exemplary usage guidance.

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