Skip to main content
Glama
Sign In

Synthex Forge — x402 Paid Agent Services

by com.synthexforge.x402
OverviewDiscussionsAdmin

Report Deadlock Breakers

report_deadlock_breakers
Read-onlyIdempotent

A cycle verdict alone does not tell an operator what to do. use it rather than assess_agent_deadlock for deadlock breakers, not agent deadlock; an object with 59 fields including action, acyclic. $0.25 USDC.

Input Schema

NameRequiredDescriptionDefault
graph.graph_idNo[POST /v1/autonomy/deadlock-detect]
commitments.agent_idNo[POST /v1/autonomy/commitment-check]
graph.wait_for_edgesNo[POST /v1/autonomy/deadlock-detect]
commitments.commitmentsNo[POST /v1/autonomy/commitment-check]
commitments.observationsNo[POST /v1/autonomy/commitment-check]

Output Schema

NameRequiredDescriptionDefault
atNoThe `at` field of the folded answer.
idNoThe `id` field of the folded answer.
okNoWhether every inner call succeeded.
dueNoThe `due` field of the folded answer.
rawNoThe `raw` field of the folded answer.
kindNoThe `kind` field of the folded answer.
noteNoThe `note` field of the folded answer.
textNoThe `text` field of the folded answer.
typeNoThe `type` field of the folded answer.
countNoThe `count` field of the folded answer.
cycleNoThe `cycle` field of the folded answer.
edgesNoThe `edges` field of the folded answer.
indexNoThe `index` field of the folded answer.
notesNoThe `notes` field of the folded answer.
sinceNoThe `since` field of the folded answer.
stateNoThe `state` field of the folded answer.
actionNoThe `action` field of the folded answer.
agentsNoThe `agents` field of the folded answer.
cyclesNoThe `cycles` field of the folded answer.
detailNoThe `detail` field of the folded answer.
lengthNoThe `length` field of the folded answer.
reasonNoThe `reason` field of the folded answer.
statesNoThe `states` field of the folded answer.
statusNoThe `status` field of the folded answer.
waiterNoThe `waiter` field of the folded answer.
acyclicNoThe `acyclic` field of the folded answer.
outcomeNoThe `outcome` field of the folded answer.
resultsNoOne result per inner call.
summaryNoOne-line summary of the folded answer.
agent_idNoThe `agent_id` field of the folded answer.
evidenceNoThe `evidence` field of the folded answer.
graph_idNoThe `graph_id` field of the folded answer.
resourceNoThe `resource` field of the folded answer.
exceptionNoThe `exception` field of the folded answer.
wait_typeNoThe `wait_type` field of the folded answer.
cycle_sizeNoThe `cycle_size` field of the folded answer.
waiting_onNoThe `waiting_on` field of the folded answer.
commitmentsNoThe `commitments` field of the folded answer.
cycle_countNoThe `cycle_count` field of the folded answer.
match_methodNoThe `match_method` field of the folded answer.
observationsNoThe `observations` field of the folded answer.
state_countsNoThe `state_counts` field of the folded answer.
commitment_idNoThe `commitment_id` field of the folded answer.
edge_coverageNoThe `edge_coverage` field of the folded answer.
kept_fractionNoThe `kept_fraction` field of the folded answer.
cycle_detectedNoThe `cycle_detected` field of the folded answer.
observation_idNoThe `observation_id` field of the folded answer.
agents_in_graphNoThe `agents_in_graph` field of the folded answer.
commitment_textNoThe `commitment_text` field of the folded answer.
breaker_priorityNoThe `breaker_priority` field of the folded answer.
commitment_countNoThe `commitment_count` field of the folded answer.
observation_textNoThe `observation_text` field of the folded answer.
edge_count_usableNoThe `edge_count_usable` field of the folded answer.
observation_countNoThe `observation_count` field of the folded answer.
checkable_fractionNoThe `checkable_fraction` field of the folded answer.
edge_count_suppliedNoThe `edge_count_supplied` field of the folded answer.
observation_outcomeNoThe `observation_outcome` field of the folded answer.
recommended_breakerNoThe `recommended_breaker` field of the folded answer.
self_reported_statusNoThe `self_reported_status` field of the folded answer.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior. The description adds meaningful behavioral context beyond annotations by disclosing the $0.25 USDC cost and noting the output object has 59 fields including action and acyclic, though it does not discuss payment timing, failure charging, or other operational constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and does not waste many words, but the structure is fragmented: the lowercase "use" after a period, the semicolon joining usage guidance to output shape, and the dangling "$0.25 USDC" make it feel terse rather than cleanly front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The schema covers parameters, an output schema exists, and annotations cover safety, so much of the calling context is provided elsewhere. The description still leaves the core concept of "deadlock breakers" underdefined and only partially explains how this differs operationally from `assess_agent_deadlock`.

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 the schema already documents all five parameters at baseline adequacy. The description adds no parameter-level meaning beyond the schema, and the schema's own descriptions are mostly endpoint tags rather than rich semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The name/title and the phrase "deadlock breakers, not agent deadlock" imply the purpose, and it explicitly contrasts with `assess_agent_deadlock`. However, the description never states a clean verb+resource definition such as "reports deadlock breakers for a cycle"; the first sentence is abstract and the purpose remains somewhat inferred.

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?

It explicitly tells the agent to use this rather than `assess_agent_deadlock` for deadlock breakers and explicitly excludes agent deadlock. That gives both an alternative and a when-not condition, which is the core requirement for top usage guidance.

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

All Synthex Forge — x402 Paid Agent Services toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources