Skip to main content
Glama

Create targeted brief

create_brief

Write a Markdown brief to hand a scoped task to another agent: set the goal, scope, exclusions, and design basis, while avoiding chat history and out-of-project files.

Instructions

Use when the user wants a scoped task written down for another agent or session: this writes a new brief Markdown record under .notch/briefs/ from the fields you supply and returns the record with its path. It stores only what you pass — it never reads chat history — and it refuses scope files outside the project root or content the secret scanner flags.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
goalYesWhat the target agent should accomplish; rendered as the brief's goal section.
tagsNoLowercase slug tags (a-z, 0-9, hyphen) for later filtering; must be unique.
scopeYesBoundaries of the work: in-scope topics, in-scope files, and an optional timeframe.
titleYesShort human-readable title for the brief; also used to build the stored filename.
actorNameNoName recorded as the author of this write; defaults to the server's configured actor, or 'mcp-client'.
exclusionsYesOut-of-scope items and known pitfalls; rendered as the brief's Known Pitfalls list.
constraintsNoHard limits the target agent must respect; accepted for compatibility but not written into the record by the MCP server — put binding limits in designBasis or exclusions.
designBasisYesThe reasoning and constraints the current design rests on, so the target agent does not relitigate settled ground.
targetAgentYesAgent or role this brief is written for; slugified into the filename and matched exactly by the list_briefs targetAgent filter.
relevantFilesNoSource links worth reading (kind: file, url, commit, issue, record, command, or repo); file links must resolve inside the project root.
recommendedNextStepsNoConcrete next actions; rendered as the brief's Recommended Next Steps list.
priorReasoningSummaryYesCondensed record of decisions already made and why, carried forward instead of raw conversation.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed15 schema fields changedv0.7.2
    • addedInput schema / properties / actorName / description
      Added value: +"Name recorded as the author of this write; defaults to the server's configured actor, or 'mcp-client'."
    • addedInput schema / properties / constraints / description
      Added value: +"Hard limits the target agent must respect; accepted for compatibility but not written into the record by the MCP server — put binding limits in designBasis or exclusions."
    • addedInput schema / properties / designBasis / description
      Added value: +"The reasoning and constraints the current design rests on, so the target agent does not relitigate settled ground."
    • addedInput schema / properties / exclusions / description
      Added value: +"Out-of-scope items and known pitfalls; rendered as the brief's Known Pitfalls list."
    • addedInput schema / properties / goal / description
      Added value: +"What the target agent should accomplish; rendered as the brief's goal section."
    • addedInput schema / properties / priorReasoningSummary / description
      Added value: +"Condensed record of decisions already made and why, carried forward instead of raw conversation."
    • addedInput schema / properties / recommendedNextSteps / description
      Added value: +"Concrete next actions; rendered as the brief's Recommended Next Steps list."
    • addedInput schema / properties / relevantFiles / description
      Added value: +"Source links worth reading (kind: file, url, commit, issue, record, command, or repo); file links must resolve inside the project root."
    • addedInput schema / properties / scope / description
      Added value: +"Boundaries of the work: in-scope topics, in-scope files, and an optional timeframe."
    • addedInput schema / properties / scope / properties / files / description
      Added value: +"Project-relative paths in scope; each must resolve inside the project root or the call is rejected."
    • addedInput schema / properties / scope / properties / timeframe / description
      Added value: +"Optional free-text period the brief covers, in the user's own wording."
    • addedInput schema / properties / scope / properties / topics / description
      Added value: +"In-scope subject areas; rendered as the brief's relevant-background list."
    • addedInput schema / properties / tags / description
      Added value: +"Lowercase slug tags (a-z, 0-9, hyphen) for later filtering; must be unique."
    • addedInput schema / properties / targetAgent / description
      Added value: +"Agent or role this brief is written for; slugified into the filename and matched exactly by the list_briefs targetAgent filter."
    • addedInput schema / properties / title / description
      Added value: +"Short human-readable title for the brief; also used to build the stored filename."
  2. First observedv0.7.1

TDQS

A4/5.0
Behavior4/5

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

Beyond the annotations (which indicate a non-read-only, non-destructive write), the description adds meaningful context: it stores only what is passed and never reads chat history, and it refuses scope files outside the project root or content flagged by the secret scanner. This is valuable safety/privacy transparency not present in the 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?

Two sentences, front-loaded with the purpose trigger and then providing key behavioral constraints. Every word earns its place; no fluff or repetition of schema content.

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 tool with 12 parameters, no output schema, and nested objects, the description gives enough orientation: what it creates, where, what it returns (record with path), and key acceptance/rejection rules. It does not need to enumerate parameters because the schema handles that, and the return type is summarized adequately.

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 all 12 parameters are already well-documented in the input schema. The description adds no new parameter-specific semantics, merely restating the scope-file constraint already in the schema. Baseline 3 applies due to full schema coverage.

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 uses a specific verb (“writes”) and resource (“brief Markdown record”) with a location (.notch/briefs/), clearly stating what the tool does. It also frames it as “scoped task written down for another agent or session,” which distinguishes it from sibling tools like create_packet, though it does not explicitly name alternatives.

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 opens with “Use when the user wants a scoped task written down for another agent or session,” providing a clear trigger condition. It does not explicitly state when not to use it or name alternative tools, but the context is strong enough for basic routing among siblings.

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

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/coldlogicAI/3notch'

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