Skip to main content
Glama
Sign In
M-Pineapple

Msty Admin MCP

by M-Pineapple
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Bloom evaluate model

bloom_evaluate_model

Run a Bloom behavioral evaluation on a local Ollama model; return JSON quality_score or an honest error with null rather than a fabricated score. Validate first; requires API key and a Bloom checkout.

Instructions

Run a Bloom behavioural evaluation on a local model. Never invents a score. Needs ANTHROPIC_API_KEY and a Bloom checkout. Use bloom_validate_model first. Calls the network. Returns JSON with quality_score or an honest error and quality_score null.

Input Schema

NameRequiredDescriptionDefault
modelYesLocal Ollama model name, for example llama3.2:3b.
behaviorYesBloom behaviour id from bloom_list_behaviors.
max_turnsNoMaximum conversation turns per scenario. Integer 1 to 10. Default 2.
total_evalsNoNumber of evaluation scenarios. Integer 1 to 20. Default 3.
task_categoryNoOptional task category for thresholds. Omit for default.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv6.2.1
    • addedInput schema / properties / behavior / description
      Added value: +"Bloom behaviour id from bloom_list_behaviors."
    • addedInput schema / properties / max_turns / description
      Added value: +"Maximum conversation turns per scenario. Integer 1 to 10. Default 2."
    • addedInput schema / properties / model / description
      Added value: +"Local Ollama model name, for example llama3.2:3b."
    • addedInput schema / properties / task_category / description
      Added value: +"Optional task category for thresholds. Omit for default."
    • addedInput schema / properties / total_evals / description
      Added value: +"Number of evaluation scenarios. Integer 1 to 20. Default 3."
  2. First observedv5.0.0

TDQS

A4.5/5.0
Behavior5/5

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

Adds substantial context beyond annotations: discloses auth requirements, network usage, an anti-hallucination guarantee ('Never invents a score'), and failure behavior ('honest error and quality_score null'). This meaningfully extends the openWorldHint/non-idempotent annotations.

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

Conciseness5/5

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

Five tight sentences with zero filler, front-loading the core action followed by prerequisites and return behavior. Every sentence 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?

Covers prerequisites, sequencing, network behavior, and return contract. Even without an output schema, the description would suffice; with the output schema present, nothing an agent needs to call correctly 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%, so parameters are fully documented in the schema. The description adds no parameter-level detail (no mention of model, behavior, max_turns, etc.), leaving the baseline of 3 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?

States a specific verb+resource: 'Run a Bloom behavioural evaluation on a local model.' The prerequisite reference to bloom_validate_model distinguishes it from that sibling and clarifies its role in the workflow.

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?

Provides explicit prerequisites ('Needs ANTHROPIC_API_KEY and a Bloom checkout') and an ordering constraint ('Use bloom_validate_model first'). Doesn't state when to avoid the tool or name alternatives beyond the prerequisite, but the sequencing guidance is clear.

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