Skip to main content
Glama

desk_add

Adds a question or station permission refusal to a project desk, with recommendation, options, context, blockers, and target person so they can answer from their own session.

Instructions

Put a question for the person on the desk (one desk for every project; numbered D1, D2...): the question, your recommendation and why, the options, two lines of context, what it blocks (tickets, stations), whether it blocks, and who asked. to is the person it is for (a person id or an email): it shows in their my_work, and only what they typed in their own sessions answers it. Left out, it goes to the assignee of the first ticket in tickets that has one, else the project's lead, else the person whose key this is. For the batch of assumptions to confirm once per milestone, pass their numbers in assumptions. Then ask the person in your session, one item at a time, blockers first. Only the orchestrator writes the desk.

A permission a station was refused: station its name and command the exact command it was refused, verbatim as it reported it; recommendation the grant in plain words (which station may run what, where). The person can allow it with one click in the Tares console; the crew's watch then restarts that station with the grant in its settings.

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": {
      "question": "<question>",
      "recommendation": "<recommendation>",
      "why": "<why>"
    },
    "name": "desk_add"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNo
whyYes
blocksNo
commandNo
contextNo
optionsNo
projectNo
stationNo
ticketsNo
asked_byNo
blockingNo
questionYes
assumptionsNo
recommendationYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.57.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does a lot: it defines the default recipient resolution chain ('assignee of the first ticket in `tickets` that has one, else the project's lead, else the person whose key this is'), and who may answer ('only what they typed in their own sessions answers it'), plus the downstream permission-grant flow after a station is refused. It still omits mutation semantics an agent would want — duplicate detection, whether re-adding the same question is idempotent, or what happens on a failed write — so it is rich but not complete for a 14-parameter write tool.

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?

Content is dense and mostly earns its place, but it is presented as two long run-on blocks rather than structured clauses, so the critical recipient-routing rule is buried mid-paragraph. The first sentence is an unstructured eight-item list of what goes on the desk, which forces the reader to parse rather than scan.

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 a 14-parameter, annotation-free write tool the description covers purpose, recipient resolution, downstream answering workflow, and a specialized permission-refusal path, and an output schema exists so return values need no explanation. The residual gaps are the unexplained `project` parameter and the absence of any error or duplicate-handling note.

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?

Compensates strongly for 0% schema description coverage by narrating nearly every field: `to` (recipient with full fallback chain), `assumptions`, `station` and `command` (with a precise 'verbatim as it reported it' constraint), `recommendation`, `options`, `context` ('two lines of context'), `tickets`/`blocks`/`blocking`, and `asked_by`. Only `project` is left implicit, inferred from 'one desk for every project', so one of 14 parameters remains unstated.

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?

Opens with a concrete verb and resource: 'Put a question for the person on the desk (one desk for every project; numbered D1, D2...)', which tells an agent exactly what object is created and where it lands. It never names the sibling tools (desk_answer, desk_list, desk_withdraw, my_work) even though it mentions my_work only as a visibility surface, so differentiation from those siblings must be inferred from the verb 'put'.

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 real usage conditions: 'Only the orchestrator writes the desk', 'Then ask the person in your session, one item at a time, blockers first', and a specific trigger for the `assumptions` path ('the batch of assumptions to confirm once per milestone'). What is missing is an explicit exclusion — it never says when to use desk_answer or desk_list instead of writing a new item, but the write-vs-read distinction is strongly implied.

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