Skip to main content
Glama

Planner (proof-of-done)

by com.monopoly-gold.planner
OverviewDiscussionsAdmin

goal-request-ac-change

Request a change to an acceptance criterion. grounds=unreachable (default): the AC cannot be proven — requires ≥3 failed evidence attempts (weak/mismatch) with 0 matches. grounds=wrong_criterion: the AC measures the wrong thing (owner never approved this wording, or a revealed fact shows it tracks something else) — no failed attempts required, but you MUST pass quotedFragment: a verbatim slice of the criterion text you claim is wrong (checked against the stored text), and the reason must name the unapproved wording or the finding; difficulty alone is rejected. An LLM judge screens the reason either way. On pass, creates an escalation for the goal owner to resolve (edit AC text, split to sub-goal, drop AC without creating a child, or reject). Grove mode only, goal must be in_progress.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
reasonYesStructured justification. For unreachable: what is unreachable and what was attempted. For wrong_criterion: which wording/threshold the owner never approved, or what finding showed the criterion measures something else
groundsNoSubject of the request: 'unreachable' (default) or 'wrong_criterion'unreachable
criterionIdYesUUID of the acceptance criterion to escalate
quotedFragmentNoVerbatim slice of the criterion text claimed to be wrong — required when grounds=wrong_criterion, ignored otherwise

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / quotedFragment
      Added value: +{
+  "default": null,
+  "description": "Verbatim slice of the criterion text claimed to be\nwrong — required when grounds=wrong_criterion,\nignored otherwise",
+  "type": "string"
+}
  2. Changed2 schema fields changed
    • addedInput schema / properties / grounds
      Added value: +{
+  "default": "unreachable",
+  "description": "Subject of the request: 'unreachable' (default) or 'wrong_criterion'",
+  "type": "string"
+}
    • changedInput schema / properties / reason / description
      Previous value: -"Structured justification: what is unreachable and what was attempted"New value: +"Structured justification. For unreachable: what is\nunreachable and what was attempted. For wrong_criterion:\nwhich wording/threshold the owner never approved, or what\nfinding showed the criterion measures something else"
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say the tool is not read-only and not idempotent; the description adds meaningful behavioral context: an LLM judge screens the reason, quotedFragment is checked against stored text, and a successful request creates an escalation for the goal owner. It also discloses the possible resolution outcomes, making the post-call behavior clear.

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

Conciseness5/5

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

The description is dense but well-structured: a clear purpose sentence, followed by ground-specific rules, validation details, and outcome information. Every clause earns its place, and the length is justified by the branching logic of two ground types plus prerequisites.

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?

The description covers prerequisites (Grove mode, in_progress goal), evidence requirements, validation rules, rejection of weak reasons, and post-escalation behaviors. It does not specify the exact return value on rejection, but this is minor given how thoroughly it guides correct use; the agent has enough to invoke the tool correctly.

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

Parameters5/5

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

Although schema coverage is 100%, the description adds significant semantics beyond the schema: it explains how grounds changes requirements, what quotedFragment must contain and that it is verified, and what the reason field must articulate for each grounds value. This materially helps an agent construct valid arguments.

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 opening sentence states a specific verb and resource: 'Request a change to an acceptance criterion.' The description then clarifies this is an escalation request rather than a direct edit by noting it 'creates an escalation for the goal owner to resolve,' which separates it from siblings like goal-update-criterion and goal-remove-criterion.

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

Usage Guidelines4/5

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

The description gives detailed conditions for when each grounds value is appropriate: unreachable requires ≥3 failed evidence attempts, while wrong_criterion requires no failed attempts but mandates a quotedFragment. It also explicitly excludes difficulty alone as a valid reason and scopes usage to Grove mode with in_progress goals. It does not explicitly name sibling alternatives, though it implies them through the escalation flow.

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

All Planner (proof-of-done) 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