Skip to main content
Glama

Commit reviewed updates

commit_reviewed_updates
DestructiveIdempotent

Writes selected CRM changes and can overwrite existing values. First confirm freezes approved IDs. Explicit decline-all: selected_proposal_ids:[], confirm:true. Wait/do not save yet: leave pending. execution_pending: unchanged receipt/key/full IDs continue the frozen selection. Replaying a completed request returns its outcomes without new writes. Poll execution_in_progress via get_review_status with backoff; read outcomes_page there. execution_state_unknown: stop and inspect CRM; never auto-retry/re-review. Expired: retained exact replay only, else inspect CRM. Current role/policy/scope/schema/revision/audit/automation guards apply. Include prerequisites; failed/queued/unknown creates block dependents. Results can include per-row outcomes and a summary.

When to use: After explicit approval/decline-all; exact replays only.

Example: Save only the company's city change from this review.

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": {
      "receipt": "<receipt>",
      "selected_proposal_ids": "<selected_proposal_ids>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "commit_reviewed_updates"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNoTrue only for explicit approval or decline-all ([]); false runs nothing.
receiptYesUnchanged review receipt.
idempotency_keyYesApproval UUID (normally review_id); reuse on continuation/replay.
selected_proposal_idsYesUnique approved IDs; [] to decline all.

Output Schema

NameRequiredDescriptionDefault
noteNo
summaryNo
outcomesNo
replayedNo
confirmedNo
review_idNo
outcomes_pageNo
review_commitNo
request_statusNo
response_guidanceNo
selection_mismatchNo
frozen_selected_proposal_idsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / confirm / description
      Previous value: -"True only after approval; otherwise nothing executes."New value: +"True only for explicit approval or decline-all ([]); false runs nothing."
    • changedInput schema / properties / selected_proposal_ids / description
      Previous value: -"Unique approved proposals/proposal_manifest IDs; frozen at confirmation."New value: +"Unique approved IDs; [] to decline all."
  2. Changed1 schema field changed
    • addedOutput schema / properties / response_guidance
      Added value: +{
      +  "properties": {},
      +  "type": "object"
      +}
  3. Changed9 schema fields changed
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true to execute; omitted or false commits nothing and returns a prompt to get the user's explicit approval first."New value: +"True only after approval; otherwise nothing executes."
    • changedInput schema / properties / idempotency_key / description
      Previous value: -"A UUID minted once per review (normally the returned review_id); reuse the same key to replay stored outcomes instead of executing again."New value: +"Approval UUID (normally review_id); reuse on continuation/replay."
    • changedInput schema / properties / receipt / description
      Previous value: -"The receipt string returned by review_proposed_updates, passed back unchanged (it is bound to that review, this workspace and user, and expires)."New value: +"Unchanged review receipt."
    • changedInput schema / properties / selected_proposal_ids / description
      Previous value: -"The review's proposal ids (its proposals[].id) the user explicitly approved — unique, each present in the receipt; the first confirmed call freezes this set."New value: +"Unique approved proposals/proposal_manifest IDs; frozen at confirmation."
    • changedInput schema / properties / selected_proposal_ids / maxItems
      Previous value: -50New value: +500
    • changedOutput schema / properties / outcomes / items / properties / record / properties / name / description
      Previous value: -"Reserved for a display label; not populated yet."New value: +"Reserved; omitted."
    • addedOutput schema / properties / outcomes_page
      Added value: +{
      +  "properties": {
      +    "next_offset": {
      +      "type": [
      +        "number",
      +        "null"
      +      ]
      +    },
      +    "offset": {
      +      "type": "number"
      +    },
      +    "total": {
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "offset",
      +    "next_offset",
      +    "total"
      +  ],
      +  "type": "object"
      +}
    • addedOutput schema / properties / summary / properties / in_progress
      Added value: +{
      +  "maximum": 9007199254740991,
      +  "minimum": -9007199254740991,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / summary / properties / pending
      Added value: +{
      +  "maximum": 9007199254740991,
      +  "minimum": -9007199254740991,
      +  "type": "integer"
      +}
  4. Changed1 schema field changed
    • removedInput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
  5. Changed2 schema fields changed
    • removedInput schema / properties / idempotency_key / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • removedInput schema / properties / selected_proposal_ids / items / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
  6. Changed11 schema fields changed
    • removedOutput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • removedOutput schema / additionalProperties
      Removed value: -{}
    • removedOutput schema / properties / frozen_selected_proposal_ids / items / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • removedOutput schema / properties / outcomes / items / additionalProperties
      Removed value: -false
    • removedOutput schema / properties / outcomes / items / properties / approval_id / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • removedOutput schema / properties / outcomes / items / properties / proposal_id / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • removedOutput schema / properties / outcomes / items / properties / record / additionalProperties
      Removed value: -false
    • removedOutput schema / properties / outcomes / items / properties / record / properties / id / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • removedOutput schema / properties / review_commit / additionalProperties
      Removed value: -{}
    • removedOutput schema / properties / review_id / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • removedOutput schema / properties / summary / additionalProperties
      Removed value: -false
  7. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say destructive, idempotent, non-read-only; the description adds the operational detail behind those hints: confirm freezes approved IDs, continuing an execution_pending request requires an unchanged receipt/key/full ID set, replays of a completed request return prior outcomes without new writes, and execution_state_unknown mandates stop-and-inspect rather than auto-retry. It also discloses the applicable guard layers and that failed/queued/unknown creates block dependents, which is exactly the beyond-annotation context this dimension rewards.

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 most important fact, that this writes and can overwrite, is front-loaded, followed by a state-by-rule layout that an agent can scan. It is telegraphic to the point of terseness in places ('Include prerequisites; failed/queued/unknown creates block dependents'), which costs some readability 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?

For a destructive, idempotent commit tool with four parameters and an output schema, the description covers prerequisites, all failure/expiry states, polling guidance, prototype-guard scoping, and partial-failure semantics. Combined with the output schema handling return values, nothing the agent needs before firing a destructive write is missing.

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 schema already explains each field and the baseline would be 3. The description goes further by giving state-conditional semantics the schema cannot: decline-all is expressed as selected_proposal_ids:[] with confirm:true, and the receipt/key must be passed unchanged to continue a frozen selection, which clarifies why confirm and the ID list interact.

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

Purpose4/5

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

The opening sentence gives a specific verb and resource ('Writes selected CRM changes') plus the crucial side effect ('can overwrite existing values'), and the 'When to use: After explicit approval/decline-all; exact replays only' line scopes it to the commit step of a review workflow. It never explicitly contrasts with update_record or propose_updates, so an agent must infer the position in the propose/review/commit chain, which keeps it below a 5.

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 enumerates when to call (post-approval, decline-all, exact replay) and when not to (wait/do not save yet, execution_state_unknown, expired without a matching replay). It names the alternative sibling for progress checks ('Poll execution_in_progress via get_review_status with backoff') and even the correct decline-all payload, so the agent has an explicit decision tree rather than inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources