Skip to main content
Glama

Record a structured external acceptance receipt (may start one repair stage)

dsh_submit_review

Records a caller-reported acceptance receipt for a settled stage, optionally starting one repair stage on fail, to gate review without executing supplied commands.

Instructions

Records a caller-reported external acceptance receipt bound to the exact latest settled stage. source=caller-reported: supplied commands and check outputs are DATA ONLY and are never executed. reviewedSource paths must be workspace-relative regular no-link files whose current SHA-256 matches. The receipt is persisted before any prompt. outcome=pass/blocked never starts the model; outcome=fail with actionable findings starts ONE repair stage in the same live session, even if host verification previously passed. Same reviewId with the same body is idempotent and never sends a second prompt; conflicting reuse is refused. Stale/in-flight/cancelled/historical/dead-runtime controls are refused without modifying files.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "taskId": "<taskId>",
      "stage": "<stage>",
      "reviewId": "<reviewId>",
      "outcome": "<outcome>",
      "summary": "<summary>"
    },
    "name": "dsh_submit_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
stageYesThe exact latest settled stage this receipt reviews.
checksNo
taskIdYes
outcomeYes
summaryYes
findingsNo
reviewIdYes
reviewedSourceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.8

TDQS

A3.9/5.0
Behavior2/5

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

The description is unusually rich on behavior: it discloses that supplied commands are never executed, that the receipt is persisted before any prompt, that reviewedSource files must be workspace-relative no-link files with matching SHA-256, and which control states are refused. However, it asserts 'Same reviewId with the same body is idempotent' while the annotations declare idempotentHint=false, a direct conflict on the same property that could mislead an agent about retry safety.

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 scope, then layered with constraints in a logical order (data-only, persistence, outcome branching, idempotency, refusals). Dense but every clause carries operational meaning; slightly long sentences reduce scannability.

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

Completeness4/5

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

For an 8-parameter mutation tool with no output schema and low schema coverage, the description covers the critical decision points an agent needs: what triggers a repair stage, what is refused, and what file preconditions apply. It does not describe what the tool returns on success or refusal, which is the main remaining gap.

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 description coverage is only 13%, so the description must compensate, and it does: it explains outcome enum semantics, reviewId idempotency/conflict behavior, stage binding to the latest settled stage, reviewedSource path and hash requirements, and that checks.command is data only. It leaves summary, findings, and checks.status semantics largely to 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 ('Records a caller-reported external acceptance receipt') plus a precise binding constraint ('bound to the exact latest settled stage'). This is clearly distinguishable from siblings like dsh_submit_task or dsh_continue_task, which do not deal with acceptance receipts.

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?

Gives explicit conditional routing: outcome=pass/blocked never starts the model, outcome=fail with actionable findings starts exactly one repair stage, and stale/in-flight/cancelled/historical/dead-runtime controls are refused. It does not name a sibling alternative for the case where the caller wants to submit work rather than a receipt, so it stops short of full when-not guidance.

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