Skip to main content
Glama
muad-yasin

The High Council

by muad-yasin
OverviewSchemaSourceRelated ServersDiscussions(1)Admin
JavaScript
Remote

Preview and price a request for outside advice

council_quote
Read-onlyIdempotent

Preview and price a request for advice from other AI labs before anything is sent or spent. Returns recipients, masked size, worst-case price, and a ten-minute quote ID.

Instructions

Preview and price a request for advice from other AI labs, before anything is sent. Nothing is sent, written or spent. Put the decision in brief (at most 48,000 characters in all; over the limit is refused, never cut; no invisible characters; no transcript, tool output, environment or file listing; not_included says what you left out). sensitivity can only tighten the operator's policy, unknown counts as confidential, and personal data or secret-adjacent material is never sent. Returns who would receive the text (lab, model, the endpoint's retention wording), its exact size and sha256 after emails, IBANs, cards, IPs, internal hosts and home paths are masked, the worst-case and expected price, and a quote_id valid for ten minutes to pass to council_advise. mode "single" asks one non-Anthropic model, chosen by advisor (the shipped default is GPT-6.1 Sol; Claude, the usual caller, and /advisor are not asked); mode "council" asks several labs and is for decisions that are hard to undo. A refusal says what to change and is final for that brief: do not retry it unchanged.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeYessingle: one non-Anthropic model; council: three labs, for hard-to-undo decisions
briefYes
advisorNosingle mode only: which model advises (default sol = GPT-6.1 Sol)
max_usdNothe most this call may spend; can only lower the limit

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.2
    • changedInput schema / properties / advisor / enum
      Previous value: -[
-  "sol",
-  "astra",
-  "gemini",
-  "deepseek",
-  "opus"
-]New value: +[
+  "sol",
+  "astra",
+  "gemini",
+  "deepseek",
+  "opus",
+  "glm-flash",
+  "qwen"
+]
  2. First observedv0.8.1

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/idempotentHint annotations: nothing is sent, written or spent; masking covers emails, IBANs, cards, IPs, internal hosts and home paths; a sha256 and exact size are computed; the quote expires in ten minutes; refusals are final and must not be retried unchanged. This is exactly the extra context annotations cannot carry.

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?

Front-loaded with what the tool does and the 'nothing is sent' guarantee, and no sentence is filler. However, it is one long semicolon-chained paragraph mixing input rules, output fields and mode semantics, which costs some scannability.

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?

There is no output schema, so the description carries the burden and does: it enumerates the return fields (recipients and retention wording, size and sha256 post-masking, worst-case and expected price, quote_id). Combined with the refusal semantics and input constraints, an agent has everything needed to call it correctly.

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

Parameters5/5

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

Adds substantial meaning beyond the 75%-covered schema: the 48,000-character ceiling on brief with 'refused, never cut', the ban on invisible characters and on transcript/tool output/environment/file listings, the 36,000-character excerpt ceiling, sensitivity only tightening policy, unknown = confidential, and the advisor default (GPT-6.1 Sol in, Claude out). Dense, high-value parameter guidance.

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 pair (preview and price) on a specific resource (a request for advice from other AI labs), and the title reinforces it. It is immediately distinguishable from the sibling council_advise, which it feeds via quote_id, and from spend_report/dry_run.

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?

Explicitly routes the agent: a quote_id is passed to council_advise, and mode 'single' vs 'council' is given a selection rule ('decisions that are hard to undo'), plus a no-retry rule for refusals. It does not state when NOT to use this versus siblings like external_prompt or dry_run, so 4 rather than 5.

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