Skip to main content
Glama
Sign In
delian

ddflow

by delian
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

ddflow_brief

START HERE every session. Returns a budgeted pack: work recoverable after a crash, the current item, what is ready to start now, why everything else is blocked, and the past lessons ranked as relevant to this task.

Instructions

START HERE every session. Returns a budgeted pack: work recoverable after a crash, the current item, what is ready to start now, why everything else is blocked, and the past lessons ranked as relevant to this task. Use this INSTEAD of reading the project's lesson or rule files: the same information, ranked for the task at hand, at a fraction of the tokens.

Input Schema

NameRequiredDescriptionDefault
itemNoFocus on this phase or task id (optional).
phaseNoRestrict the ready set to this phase (optional).
as_agentNoSubagent name, this call only.
for_agentNoRender this subagent's launch brief for item.
check_recoveryNoScan for crashed agents' worktrees and lead with them: know it BEFORE new work.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.2.7
    • changedInput schema / properties / as_agent / description
      Previous value: -"A subagent's own name, this call only."New value: +"Subagent name, this call only."
    • changedInput schema / properties / check_recovery / description
      Previous value: -"Also scan for crashed agents' worktrees and lead with them: unclaimed work left by a dead process is the one thing to know BEFORE picking up something new."New value: +"Scan for crashed agents' worktrees and lead with them: know it BEFORE new work."
    • addedInput schema / properties / for_agent
      Added value: +{
+  "description": "Render this subagent's launch brief for item.",
+  "type": "string"
+}
  2. Changed2 schema fields changedv0.1.12
    • changedInput schema / properties / as_agent / description
      Previous value: -"Subagent sharing the parent's connection: your own stable name, for this call only (see ddflow_identify)."New value: +"A subagent's own name, this call only."
    • changedInput schema / properties / check_recovery / description
      Previous value: -"Also scan for crashed agents' worktrees and lead with them. Worth it at session start: unclaimed work left by a dead process is the one thing to know BEFORE picking up something new."New value: +"Also scan for crashed agents' worktrees and lead with them: unclaimed work left by a dead process is the one thing to know BEFORE picking up something new."
  3. Changed1 schema field changedv0.1.10
    • addedInput schema / properties / as_agent
      Added value: +{
+  "description": "Subagent sharing the parent's connection: your own stable name, for this call only (see ddflow_identify).",
+  "type": "string"
+}
  4. First observedv0.1.0

TDQS

A4.1/5.0
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 discloses that output is a token-budgeted, relevance-ranked pack and that it surfaces crash recovery, which is useful context, but it never explicitly states that the call is read-only/safe, nor what happens with no active work, nor how the budget behaves. Adequate but not complete for an unannotated tool.

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 the imperative "START HERE every session" and only three sentences. Slight redundancy between "ranked as relevant to this task" and the closing "ranked for the task at hand, at a fraction of the tokens" keeps it from a 5.

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?

There is no output schema, so the description's enumeration of pack contents usefully stands in for return-value documentation, and it explains the value proposition versus raw file reading. What remains thin is behavior for edge cases and how the optional focus parameters alter the pack, but the schema already covers parameter meaning.

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 each of the five optional parameters is already documented. The description only indirectly touches two of them (crash recovery maps to check_recovery; task-relevant ranking maps to item), adding little beyond the schema, so the baseline 3 applies.

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 states exactly what the tool returns and enumerates the pack contents (crash-recoverable work, current item, ready set, blockers, ranked lessons). It also distinguishes itself from the sibling lesson_search/rule_list style tools by saying to use this instead of reading the project's lesson or rule files.

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

Usage Guidelines5/5

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

"START HERE every session" gives an explicit trigger, and "Use this INSTEAD of reading the project's lesson or rule files" names the alternative and the condition for choosing this tool. Nothing about when to call it is left to inference.

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