Skip to main content
Glama
delian

ddflow

by delian
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

ddflow_identify

Declare which agent is using this connection before any write so concurrent agents in one repository keep separate claims, gate results, and reviews.

Instructions

Declare WHO you are on this connection, before doing anything that writes. Call this first if more than one agent or subagent is working this repository at the same time. Every attribution in the queue depends on it: who holds a claim, who ran a gate, and whether a review was done by an agent other than the author. By default ddflow derives an identity from the working tree, which is correct for one agent per tree and WRONG, with no error, for several in the same tree — their work merges into one identity, 'what was I doing' answers with someone else's task, and a review passes independence against itself. There is no way to detect this from the outside, so it has to be declared. Pick a name that is stable for your whole session and distinct from the other agents': your role or assignment, not a random string. Idempotent; call it again to correct it. A SUBAGENT sharing its parent's connection must NOT call this -- it would rename the parent -- and passes as_agent on each call instead (every other tool takes it; same name rules as here, equivalent to the CLI's --agent: claims, gate outcomes and reviews are attributed to that name for that one call and conflict-checked against its siblings', and the connection's identity is untouched).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agentNoA short stable name for you on this connection, e.g. 'reviewer-2' or 'importer'. Letters, digits, '.', '_' and '-' only, up to 64 characters — it becomes a log filename. OMIT it to reset to the tree-derived default and be told what that is.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.10

TDQS

A4.8/5.0
Behavior5/5

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

No annotations exist, so the description carries the full burden and does so richly: it discloses idempotency, the silent-failure mode of the tree-derived default ('WRONG, with no error'), that the failure is undetectable from outside, and the parent-renaming hazard for subagents. This is exactly the behavior an agent needs before calling.

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 core instruction, and every clause does work — the rationale, the failure mode, the naming rule, and the subagent exception are all load-bearing. It is dense and long, but for a subtle tool whose misuse is silent, the length is largely justified rather than padding.

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?

With one optional parameter, no output schema, and no annotations, the description supplies everything needed: default behavior, reset semantics, the subagent exception, and the consequences of getting identity wrong. Nothing required for correct invocation is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description adds genuine meaning beyond the schema by prescribing naming semantics ('stable for your whole session', 'your role or assignment, not a random string') and by noting the reset-to-default behavior of omission. The character/format rules themselves remain in the schema.

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 and resource ('Declare WHO you are on this connection') and immediately frames the scope ('before doing anything that writes'). It is unmistakably distinct from siblings like ddflow_session_start or ddflow_claim, which an agent might otherwise confuse it with.

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?

Explicit when-to-use ('Call this first if more than one agent or subagent is working this repository at the same time') and explicit when-not-to-use ('A SUBAGENT sharing its parent's connection must NOT call this'). It also names the alternative mechanism (`as_agent`) and the condition that selects it.

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