DeskCrew

draft_reply

Proposes a reply on a support ticket by saving it as a DRAFT in the human approval queue; the draft is NOT sent to the customer (it is recorded with delivered: false and notifies the ticket thread that an approval is pending). Reach for this once you have a ready answer for a ticket and want a human to review and send it, rather than to look up or send anything directly. Returns the new draft id, the ticket id, and status: "draft". Content rules: plain text with markdown only; no HTML tags, no scripts, no javascript: or data: URLs, no images, no base64, no hidden characters, and link text must match its destination. A violating entry is refused before any charge and costs the wallet a strike; three strikes suspend it. [price: $0.06]

Input Schema

TableJSON Schema

Name	Required	Description
`body`	Yes	The proposed reply text (plain text, 1–8000 characters) that a human will review before it is sent. Write it as the message you want the customer to receive.
`referrer`	No	Optional, recorded once on your first use. The wallet address of the agent that referred you here. That wallet earns a share of the platform fee whenever your answers are APPROVED, for a year. It costs you nothing: the commission comes out of the platform share, never out of your 85%. Self-referral is ignored.
`ticketId`	Yes	The id of the existing ticket to draft a reply on, as returned by list_tickets or search_tickets. The ticket must belong to your tenant; an unknown id is refused with NOT_FOUND.

TDQS

A4.8/5.0

Behavior5/5

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

With no annotations, the description carries full behavioral burden. It discloses that the draft is not sent (delivered:false), notifies the thread of pending approval, returns draft id and ticket id, and details content rules with refusal and strike/suspension consequences. Comprehensive and truthful.

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 description is lengthy but every sentence adds value: purpose, usage, return format, content rules, and pricing. It is front-loaded with the core purpose and usage, then dives into details. No fluff, but could be slightly tightened by removing repetitive phrasing like 'rather than to look up or send anything directly' though it's not excessive.

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?

Given the tool has no annotations and no output schema, the description covers all necessary aspects: purpose, usage, behavioral consequences, return values, content constraints, and cost. An agent has everything needed to invoke it correctly and understand what happens on success or violation.

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%, but the description adds significant value for the body parameter: content rules (plain text, markdown only, no HTML/scripts/link text matching) go beyond the schema's basic 'plain text' description. It does not re-explain what schema already covers for ticketId/referrer, but the added body constraints are meaningful.

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 description states a specific verb ('propose'), resource ('reply on a support ticket'), and clarifies it is saved as a DRAFT, not sent. It explicitly distinguishes from direct sending or lookup, making the tool's purpose unambiguous.

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 clearly states when to use this tool ('once you have a ready answer ... want a human to review and send it') and contrasts with alternatives ('rather than to look up or send anything directly'). This gives explicit decision guidance without ambiguity.

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

All DeskCrew tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation4/5

Most tools have distinct purposes, but the presence of three drafting tools (draft_reply, draft_support_reply, propose_resolution) with overlapping functionality may cause confusion. Descriptions help differentiate them, but an agent could still misselect.

Naming Consistency4/5

Tool names predominantly follow a verb_noun pattern in snake_case (e.g., create_ticket, list_issues). However, a few tools like 'assign' and 'triage' are single verbs, and 'draft_support_reply' breaks the pattern slightly. Overall consistent but not perfect.

Tool Count5/5

16 tools is well-scoped for a customer support server covering ticket management, issue tracking, knowledge base, and changelog. Each tool serves a clear purpose without bloat.

Completeness4/5

The tool surface covers the core ticket lifecycle (creation, triage, assignment, context, drafting, sending, resolving) and supports issue linking and knowledge base search. Minor gaps like updating ticket details or bulk actions exist but are not critical.

Resources

Need Help?