Skip to main content
Glama

ddflow_resolve

Settle a contested item by choosing which duplicate definition or lease to keep; the losing claim is released, and losing definitions can be re-added under new ids.

Instructions

Settle a CONTESTED item: two clones each added the same id with different content, or each claimed it, and a merge brought both in. ddflow_doctor names every contested item, ddflow_show lists the rival definitions (event id, agent, title, body) and claims, and ddflow_next will not offer one until it is settled. keep names the definition (event id or agent) and/or the lease holder to keep; the losing claim is released in the same transaction. A losing DEFINITION is returned in lost -- re-add it under a new id with refile_as, or it exists only in the log. Refused (exit 3) on an item that is not contested. Settle what the operator decides, not by guess.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesThe contested item.
keepYesEvent id (or a 6+ character prefix), agent, or lease holder to keep.
as_agentNoSubagent sharing the parent's connection: your own stable name, for this call only (see ddflow_identify).
refile_asNoComma-separated new ids, one per definition NOT kept, in `show` order: each is re-added under its new id in the same transaction.

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?

With no annotations, the description carries the full burden and does so well: it discloses transaction semantics ("the losing claim is released in the same transaction"), the fate of a losing definition (returned in `lost`, else exists only in the log), and error behavior (exit 3 on a non-contested item). It also warns against guessing and defers to the operator's decision.

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 action and dense but purposeful: every sentence covers contested detection, sibling tooling, keep/lost/refile_as mechanics, or the refusal condition. It is somewhat packed, but no sentence is filler.

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?

No output schema or annotations exist, and the description still explains the return of `lost`, the transactional side effects, the recovery path via `refile_as`, and the error case. An agent has enough to invoke it correctly.

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, but the description adds meaning: `keep` accepts a definition (event id or agent) and/or a lease holder, `refile_as` must be comma-separated in `show` order and re-adds each dropped definition under its new id. This clarifies intent beyond the schema strings.

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 ("Settle") and resource ("a CONTESTED item"), then defines what contested means (two clones added the same id or claimed it, brought in by a merge). It routes the agent to the sibling tools (ddflow_doctor names them, ddflow_show lists rivals), so it is clearly distinguishable from the other ddflow_* tools.

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: an item named as contested by ddflow_doctor, which ddflow_next will not offer until settled. It names the complementary tools and the exclusion condition ("Refused (exit 3) on an item that is not contested"), leaving nothing 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