Skip to main content
Glama
Sign In

SetLatch

by com.setlatch
OverviewDiscussionsAdmin

Update a task

update_task
Destructive

Update one system’s task on a request: mark it done, na (nothing held; note required) or back to todo, with an internal note, and/or set response_note, what the requester is told about that system in the response. Only the fields you pass change. Recording a task as done does not delete anything anywhere: on a deletion request, a person approves the deletion in connected apps from the SetLatch dashboard. Closing the last open task moves the request to response_ready.

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": {
      "site": "<site>",
      "request_id": "<request_id>",
      "task_id": "<task_id>"
    },
    "name": "update_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoInternal: where it was found, what was done, or why nothing was held.
siteYesThe site: its slug from list_sites (its id or exact name also work).
statusNotodo, done, or na (nothing held about the requester; needs a note).
task_idYesThe task id from get_request (one task per data map system).
request_idYesThe request id: the full id from list_requests (a unique start of it also works).
response_noteNoWhat the requester is told about this system. Empty string clears it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / status / description
      Added value: +"todo, done, or na (nothing held about the requester; needs a note)."
    • addedInput schema / properties / task_id / description
      Added value: +"The task id from get_request (one task per data map system)."
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the annotations by clarifying what destructiveHint=true actually means here: marking done deletes nothing, and on a deletion request a human approves the deletion in connected apps from the dashboard. It also discloses the non-obvious cross-entity side effect that closing the last open task flips the request to response_ready.

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?

Front-loads the action and allowed values in the first sentence, then layers constraints and side effects in descending order of importance. Every sentence contributes a distinct fact, with no restatement of the title or schema.

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 mutation tool with no output schema, it supplies what an agent needs to call it safely: which fields change, the note prerequisite for 'na', how to clear response_note, and the resulting state transition on the parent request.

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 already 100%, so the baseline is 3; the description adds real meaning on top by tying 'na' to the requirement for a note and framing response_note as what the requester is told about that system. It does not describe the site or request_id identifier formats, which the schema already covers.

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, resource and scope ('Update one system's task on a request') plus the exact fields it can change (status, note, response_note), which is enough to distinguish it from update_request_status and update_data_map_system without opening a schema.

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 clear operating conditions: partial-update semantics ('Only the fields you pass change'), the constraint that 'na' needs a note, and the downstream effect that closing the last open task moves the request to response_ready. It stops short of explicitly naming a sibling alternative for cases where the whole request rather than one task should change.

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

All SetLatch 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