Skip to main content
Glama
Sign In
Xzar MCP Server

Xzar MCP Server

Official
by xzar-si
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Start an evaluation task

start_task

Starts a new evaluation episode and returns the case instructions, episode ID, answer format, and tool budget, enabling you to begin scoring an agent on a real professional decision.

Instructions

Start a new evaluation task (one episode) and get the case. Call this first. Returns the episode id (needed by every other episode tool), the case instructions, the answer format and the tool budget. Uses one task of credit; a start that fails on Xzar's side is refunded.

Input Schema

NameRequiredDescriptionDefault
task_idNoA specific task id to retry; omit to get the next unserved case
tasksetNoWhich kind of case to work. Default patents-first-action. tariffs-classification asks for the tariff code of a real product.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.3
    • changedInput schema / properties / task_id / description
      Previous value: -"Optional specific task id"New value: +"A specific task id to retry; omit to get the next unserved case"
    • changedInput schema / properties / taskset / description
      Previous value: -"Optional task set: patents-first-action (default), patents-response or patents-appeal"New value: +"Which kind of case to work. Default patents-first-action. tariffs-classification asks for the tariff code of a real product."
    • addedInput schema / properties / taskset / enum
      Added value: +[
+  "patents-first-action",
+  "patents-response",
+  "patents-appeal",
+  "tariffs-classification"
+]
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing cost behavior ('Uses one task of credit') and the refund edge case on server-side failure, plus the critical dependency that every other episode tool needs the returned episode id. This is exactly the kind of non-obvious operational detail annotations cannot convey, and it is consistent with idempotentHint=false and readOnlyHint=false.

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?

Four short sentences, front-loaded with the action and the 'call this first' directive, and no sentence is padding. The return-value list is slightly dense but each item is used by downstream calls, so it earns its place.

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?

With no output schema, the description correctly takes on the burden of enumerating the returned fields (episode id, case instructions, answer format, tool budget) and flags the credit/refund behavior. Nothing needed to invoke it correctly or interpret its result is missing.

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 description coverage is 100% and the taskset enum is self-documenting, so the schema already carries the parameter semantics. The description adds no parameter-level detail beyond what is in the schema, so 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?

States a specific verb and resource ('Start a new evaluation task (one episode) and get the case') and immediately distinguishes it in the sibling set with 'Call this first'. Enumerates what it returns (episode id, case instructions, answer format, tool budget), so an agent knows this is the entry point rather than a sibling like submit_answer or search_library.

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

Usage Guidelines4/5

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

'Call this first' gives an explicit ordering constraint relative to the other episode tools, which is the key usage decision here. It does not state when-not to call it (e.g., reusing an existing episode), but the schema's task_id 'retry' note covers the re-entry path.

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