Skip to main content
Glama
tsarihan
by tsarihan

ask_council

Query a council of AI models and receive a structured synthesis in five modes: individual, categorized, deconflicted, pooled, or dialectic. Attach files, images, or a git diff for context.

Instructions

Send a question to the model council and get a structured response. Mode: individual (each model answers separately), categorized (judge groups responses into agreement/complementary/conflicting), deconflicted (iterative loop — judge orchestrates re-questioning until conflicts resolve, returns a deconfliction score 0–100%), pooled (Delphi-style — members reconsider against a neutral, deduplicated, attribution-free pool of answers; no winner is forced, so genuine divergence is preserved), or dialectic (thesis/antithesis/synthesis — members defend their pick and critique the rest, the judge compiles a pros/cons dossier per option, then members re-select a ranked top-3). Attach images to ask a vision question — only auto-detected vision-capable members are queried; the rest are skipped and reported in visionRouting. For a repo review, pass git_ref (e.g. "uncommitted", "main..HEAD") instead of hand-listing files — the server runs git diff locally and attaches it as context. For a full repo-wide review (not just a diff), full_repo_access (default false, WARNING: read access to the whole repo — see its param description) grants claude-cli/codex-cli members read-only browse/read access.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoResponse mode override for this call only.
filesNoOptional local file paths to read and attach as labelled context (default caps: 512 KB/file, 1.5 MB total, 32 files). Text only — use "images" for pictures.
imagesNoOptional local image paths (png/jpg/jpeg/gif/webp). Auto-detected vision-capable council members are queried with the image(s); members without vision support are automatically skipped for this call (see visionRouting in the result). Caps: 8 MB/image, 24 MB total, 6 images.
contextNoOptional background text prepended to the question for every member.
git_refNoAuto-attach a local `git diff` as context for a repo review, instead of hand-listing every changed file via "files". One of "uncommitted" (staged+unstaged vs HEAD), "staged", "unstaged", or a git revision/range (e.g. "main..HEAD"). Errors clearly on a bad ref, no changes, or a diff too large to attach (> 512 KB).
verboseNodeconflicted → include the initial categorization and per-round detail; pooled/dialectic → include the initial (round-0/thesis) raw member responses.
git_repoNoRepo directory to run git_ref in. Defaults to the working directory.
questionYesThe question or prompt to send to all council members.
full_repo_accessNoWARNING: grants claude-cli/codex-cli repo exploration for a repo-wide review — ENFORCED DIFFERENTLY per provider. claude-cli: Read/Grep/Glob CONFINED to the repo root (real enforced boundary). codex-cli: cwd points at the repo, but its read-only sandbox does NOT confine reads to it — can read anywhere the OS user can (pre-existing behavior, not added by this flag; writes stay blocked everywhere). Defaults false; confirm with the user before setting true for an interactive call (an unattended review step you already control, e.g. end-of-workflow, may set it autonomously). Other members are unaffected. Repo root: git_repo, else cwd.
reasoning_effortNoHow hard every member AND the judge think, for this call only — overrides the configured default. Higher levels give deeper answers at real cost in time and subscription quota, multiplied across members x rounds. A level the backend does not support is clamped to its nearest supported one ("max" runs as "high" on Ollama, "none" as "low" on claude-cli), so one setting works across a mixed council and no member is dropped for asking. Omit to use the configured default.
max_deconflict_roundsNoMax deconfliction rounds override for this call only.
Behavior5/5

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

Despite sparse annotations (only readOnlyHint=false), the description thoroughly discloses behavioral traits: the deconfliction loop and 0-100% score, vision member auto-detection and skipping, local git diff execution, full_repo_access safety warnings including codex-cli's non-confined read behavior, and reasoning_effort cost/clamping across rounds. This far exceeds annotation coverage and gives the agent a clear safety and side-effect picture.

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 long but information-dense, with each sentence serving a purpose: modes, vision behavior, git diff usage, full_repo_access warning, reasoning_effort. It is front-loaded with the core action, then details. It could be tightened, but for a tool with 11 parameters and multiple complex modes, the length is justified and well-organized.

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?

The tool is complex and has no output schema, yet the description covers the major behavioral outcomes: structured response, deconfliction score, visionRouting in results, verbose per-round details, and raw member responses. It does not fully describe the complete response envelope, but it provides enough context for an agent to invoke correctly and interpret core results.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds substantial meaning beyond the schema. It elaborates each mode into full operational semantics, explains the visionRouting effect for images, provides detailed git_ref value examples, and warns about full_repo_access enforcement differences per provider. This transforms bare parameter names into actionable usage knowledge.

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 clear, specific verb+resource statement: 'Send a question to the model council and get a structured response.' It then enumerates distinct modes (individual, categorized, deconflicted, pooled, dialectic) and special use cases like image questions and repo review, making the tool's scope unambiguous and clearly distinguishing it from siblings like list_models and get_council_result.

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?

The description provides concrete guidance on when to use specific features: use git_ref for repo diffs, full_repo_access for repo-wide reviews, and images for vision questions. It explains mode selection in detail. However, it does not explicitly contrast itself with ask_council_async or other sibling tools, so usage-vs-alternative guidance is incomplete.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tsarihan/model-council-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server