Skip to main content
Glama
Sign In
CoAgent8

CoAgent8

by oktawianwybieralski
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

consult

Get a second opinion on a question, design, bug, or plan from another coding agent; returns the answer plus backend, model, timing, and session handle.

Instructions

Second opinion on a question, design, bug or plan. Returns the answer, then "CoAgent8:" lines: backend, model, seconds, session handle.

Input Schema

NameRequiredDescriptionDefault
modelNoOmit unless the user names a model or price limit. doctor lists models, efforts and prices; unknown names fail. Tag ask: ask the user first, a form follows; deny: never runs.
backendNocodex: Codex CLI; claude: Claude Code; agy: Antigravity. auto (default): configured provider, else another CLI than yours, most cached quota.
proposalYesSelf-contained question or plan; name files instead of pasting them. Bad: "thoughts?"
task_typeNoOmit for a plain question; set to ask for that kind of analysis.
file_pathsNo
timeout_msNoMonotonic call budget, ms: Git, prep, consent, CLI turn, teardown.
context_filesNoWorkspace paths the agent reads itself; only the paths are sent.
session_handleNoSame-topic follow-up: footer handle; else a fresh agent rereads all.
workspace_pathNoRepository path; omit for client workspace (footer fallback).
reasoning_effortNoOmit for the default; doctor lists per-model values. Required where listed, or as a model name suffix.
output_price_belowNoUser limit, USD per million output tokens, strict (5 excludes 5). Only verified prices qualify; server picks default or newest.
specific_questionsNoExtra questions or criteria the answer must cover.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.7.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the return shape (answer followed by "CoAgent8:" footer lines including backend, model, seconds, and session handle), but it does not mention external CLI invocation, cost/quota implications, consent behavior, or whether it is safe/read-only.

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?

Two sentences, front-loaded with the purpose and followed by the return format. There is no filler; every sentence adds useful information.

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?

For a 12-parameter tool with no output schema, the description gives the essential purpose and a partial return-value explanation. Combined with the very high schema coverage, this is mostly complete, though it omits sibling differentiation and cost/consent context an agent might need.

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 92%, so the schema already documents nearly all 12 parameters in detail. The description adds no parameter-specific guidance beyond implicitly referencing the returned session handle; baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a clear specific purpose: "Second opinion on a question, design, bug or plan." It states the resource and the type of output. It does not explicitly distinguish itself from the sibling tool "review," so it falls short of a 5.

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

Usage Guidelines3/5

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

The phrase "Second opinion" implies usage after forming a proposal, but the description does not state when to use this tool versus siblings such as review or doctor. It gives no explicit exclusions or alternative-routing guidance.

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