Skip to main content
Glama
naw103

Foremerge

by naw103
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

Check intent conflicts

check_conflicts
Read-only

Ask whether planned work collides with other agents' active work before any change exists. Read-only what-if checks and published-intent findings help coordinate overlapping scopes before publishing.

Instructions

Ask whether planned work collides with other agents' active work, before any change exists. Read-only: nothing is stored, so use it while only planning. It runs the same comparison as publish_intent: overlapping scopes, not only identical ones, and the declared operations on each. Pass intent_id alone to list the persisted OPEN or COORDINATING conflicts on a published intent (use this before publish_changeset and before run_verification, since conflicts are raised when the later intent publishes). Pass intent text with scopes, or intent_id with replacement scopes, for a what-if check against every intent from INTENT through VALIDATED, excluding ACCEPTED, COMMITTED and DISCARDED; those findings carry ephemeral eph_ ids and are not recorded. Returns conflicts (each with severity, explanation, evidence and a suggested coordination step), checked_intents, blocking (true when any finding is HIGH), and the active policy. To record a decision about overlap, use record_assessment or resolve_conflict instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
intentNoFree-form summary of work not yet published, for a what-if check. Provide this or intent_id. Passing an intent id here is rejected; use intent_id.
scopesNoScopes to compare, each with the operation you would perform. With intent text, these are the proposed scopes. With intent_id, non-empty scopes replace the intent's own for this check only.
agent_idNoOptional caller agent id. Informational only; it does not change which work is compared.
intent_idNoA published intent (int_...) to check. Provide this or intent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.4.3
    • addedInput schema / properties / agent_id / description
      Added value: +"Optional caller agent id. Informational only; it does not change which work is compared."
    • addedInput schema / properties / intent / description
      Added value: +"Free-form summary of work not yet published, for a what-if check. Provide this or intent_id. Passing an intent id here is rejected; use intent_id."
    • addedInput schema / properties / intent_id / description
      Added value: +"A published intent (int_...) to check. Provide this or intent."
    • addedInput schema / properties / scopes / description
      Added value: +"Scopes to compare, each with the operation you would perform. With intent text, these are the proposed scopes. With intent_id, non-empty scopes replace the intent's own for this check only."
    • addedInput schema / properties / scopes / items / properties / key / description
      Added value: +"The name within that kind, for example PaymentService, POST /orders, or src/billing.rs. Comparison is case-insensitive."
    • addedInput schema / properties / scopes / items / properties / kind / description
      Added value: +"What sort of thing the scope names: a code symbol, an API route, a data schema, a config key, infrastructure, a test, a migration, an environment variable, a file path, a component, a contract, or a broader domain."
  2. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already establish read-only/non-destructive, but the description adds substantial context: nothing is stored for a what-if check, persisted findings are limited to OPEN/COORDINATING conflicts, what-if findings get ephemeral eph_ ids and are not recorded, the state filter excludes ACCEPTED/COMMITTED/DISCARDED, and blocking is true when any finding is HIGH. No conflict with the declared annotations.

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?

The purpose is front-loaded in the first sentence and follow-on sentences cover mode selection, state filtering, and return shape, each earning its place. It is dense and long, but for a two-mode tool with no output schema the length is largely justified rather than padded.

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 no output schema, the description carries the return burden and does so: conflicts (severity, explanation, evidence, suggested coordination step), checked_intents, blocking, and the active policy. Combined with the state-filter and ephemeral/persisted distinction, an agent has everything needed to call and interpret it.

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 goes beyond the per-field schema text by explaining how the parameters combine: intent_id alone lists persisted conflicts, intent text with scopes is a what-if check, and non-empty scopes with intent_id replace the intent's own scopes for that check only. That combination logic is genuinely additive.

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 a specific verb and resource — asking whether planned work collides with other agents' active work, before any change exists. It explicitly differentiates itself from publish_intent (same comparison, but for publishing) and from record_assessment/resolve_conflict (recording a decision), so an agent can route correctly without opening schemas.

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?

Offers explicit timing ('use it while only planning', 'use this before publish_changeset and before run_verification') and names the alternatives to use when the goal is to record rather than check. Both invocation modes are framed with their selecting conditions (intent_id alone vs intent text vs intent_id plus replacement scopes).

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