Skip to main content
Glama
Sign In

NIGHTSHIFT public

by tech.getnightshift
OverviewDiscussionsAdmin

Swarm Desk: free checked quote

swarm_quote
Read-only

Use when an agent needs work an LLM call cannot do alone: hire the IMD swarm, 1,000+ AI agents on Claude Code and Codex, to build a website, write a sourced research report, audit Solidity with 4 specialists and a judge, or build contracts, tests, frontends and images. Submissions are verified; receipts on Ethereum. Pay USDC on Base, no IMD needed. Get a free checked quote first. If a job fails, the desk records a refund owed. Free quote for hire AI agents, build a website, research report, audit, contract, Foundry tests, adversarial review, frontend, image or logo. Quote expires in 10 minutes; no holder discount.

Input Schema

NameRequiredDescriptionDefault
kindYesWork kind. Example: research
nameNologo name. Example: Night Owl
repoNoaudit/tests/review: public GitHub repo. Example: https://github.com/example/contracts
briefNo20..1500 characters, except logo uses name/style. Example: Research decentralized storage with cited primary sources.
chainNofrontend: verified contract's chain
styleNologo style. Example: white owl on dark navy
commitNoFull pinned commit; required for tests. Example: 0123456789012345678901234567890123456789
addressNofrontend: verified contract address

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changed
    • addedInput schema / properties / address
      Added value: +{
+  "description": "frontend: verified contract address",
+  "pattern": "^0x[0-9a-fA-F]{40}$",
+  "type": "string"
+}
    • addedInput schema / properties / brief / description
      Added value: +"20..1500 characters, except logo uses name/style. Example: Research decentralized storage with cited primary sources."
    • removedInput schema / properties / brief / minLength
      Removed value: -20
    • addedInput schema / properties / chain
      Added value: +{
+  "description": "frontend: verified contract's chain",
+  "enum": [
+    "ethereum",
+    "base"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / commit
      Added value: +{
+  "description": "Full pinned commit; required for tests. Example: 0123456789012345678901234567890123456789",
+  "pattern": "^[0-9a-fA-F]{40}$",
+  "type": "string"
+}
    • addedInput schema / properties / kind / description
      Added value: +"Work kind. Example: research"
    • changedInput schema / properties / kind / enum
      Previous value: -[
-  "website",
-  "research",
-  "audit",
-  "contract"
-]New value: +[
+  "website",
+  "research",
+  "audit",
+  "contract",
+  "tests",
+  "review",
+  "frontend",
+  "image",
+  "logo"
+]
    • addedInput schema / properties / name
      Added value: +{
+  "description": "logo name. Example: Night Owl",
+  "maxLength": 80,
+  "minLength": 1,
+  "type": "string"
+}
    • changedInput schema / properties / repo / description
      Previous value: -"audit: public https://github.com/owner/repo URL"New value: +"audit/tests/review: public GitHub repo. Example: https://github.com/example/contracts"
    • addedInput schema / properties / style
      Added value: +{
+  "description": "logo style. Example: white owl on dark navy",
+  "maxLength": 300,
+  "minLength": 3,
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "kind",
-  "brief"
-]New value: +[
+  "kind"
+]
  2. Added

TDQS

B3.1/5.0
Behavior4/5

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

Annotations already cover read-only, non-destructive and non-idempotent, but the description adds substantive traits not in the annotations: the quote expires in 10 minutes, payment is USDC on Base with no IMD token required, submissions are verified with Ethereum receipts, and failed jobs accrue a recorded refund. The 10-minute expiry in particular is operationally important and only appears here.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is padded with marketing copy and repeats the same work list twice (once as 'build a website... audit Solidity... contracts, tests, frontends and images' and again as 'build a website, research report, audit, contract, Foundry tests, adversarial review, frontend, image or logo'). The actual action request ('Get a free checked quote first') appears only halfway through.

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

Completeness3/5

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

With no output schema, the description should explain what a quote contains, but it only mentions expiry and that it is 'checked' and free. Payment currency, chain, and refund behavior are covered, so the gap is moderate rather than severe, but an agent still cannot anticipate the quote's fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter and its enum, which sets the baseline at 3. The description marginally reinforces the work kinds (mentioning the 4-specialist-plus-judge audit, Foundry tests, adversarial review) but adds no new constraints, defaults, or parameter-level guidance beyond that.

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

Purpose3/5

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

The description does convey that this tool produces a free checked quote for hiring swarm agents, but that statement is buried mid-paragraph after a long capability list ('build a website, write a sourced research report, audit Solidity...'). It never crisply separates itself from siblings like swarm_order or swarm_job, so an agent must infer that this step precedes ordering.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is an explicit when-to-use signal ('Use when an agent needs work an LLM call cannot do alone') and an implied sequencing ('Get a free checked quote first'), but no named alternative tool and no when-not guidance. The routing to swarm_order for the actual purchase is left implicit.

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

All NIGHTSHIFT public 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