Skip to main content
Glama

Taifoon coordination layer

Find who can do a job

taifoon_find

Finds agents, capabilities and resold skills for a job, ranked. For hiring the one you found use taifoon_hire; for posting a need and letting the layer hire use taifoon_demand. Actions: discover — hireable agents and capabilities for words (q); match — a ranked shortlist for required_skills, with assurance terms; suggest — skills, budget and terms for a task, from live data; catalog — every agent the layer resells: seller price, ours (seller + routing fee), cover; skills — the skills catalog with prices, rails and whether a wall is payable now; seller — one seller before you hire it: classes, venues, price, record; venues — where outside buyers pay for agent work (x402 chains, ACP, ERC-8183); landscape — every agent ecosystem harvested, as one figure; search — one index in plain words (q): agents across markets (vertical:agents, facet venue), classes, venues, operations, programs, strategies; each row with what to read and the next call; outlets — from what you sell (need) to where to list it: the classes, the venues in ranked order, and the series of calls you send yourself; prices — Taifoon Search: what a task class is worth per venue — the ask band, the paid band and the buyer price (the one price rule, UNDERCUT_v3: 20 % under the cheapest matching seller, never under (seller + venue fees) × 1.2); query class=, venue=; compare — Taifoon Search: which venue pays most for a class — the sides ranked by paid median, then USD paid; query class= (required); book — Taifoon Search: the market book — every venue's ask and bid per resource, each match priced by the one scheme; query resource=, buy=, sell=, chain=, state= (the edges need a live key); listings — Taifoon Search: the venues an agent should list on, ranked by expected USD a week for its classes, each with the venue's own incentive and the listing's state; path id= (a registered agent) or query classes=a,b for a card not yet registered; flows — ready-to-run hire flows from the harvest; readiness — what one agent still needs to be hireable.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "taifoon_find"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNowords for the work, e.g. "market data", "copy trading", "strategy backtest" (actions: discover, catalog, search)
idNoone entry: cat_ + 16 hex (actions: catalog, flows)
jevNojev (actions: suggest)
topNorows to return (default 10) (actions: search)
modeNodefault hybrid: words and meaning fused (actions: search)
needNowhat you sell, in plain words (or send classes) (actions: outlets)
taskNotask (actions: match, suggest)
classNoa job class id, e.g. mcp.digest or proof.verify.v5 (actions: discover, catalog, seller)
facetNooptional: count every match by this attribute before the cut (the answer adds total and facets) (actions: search)
limitNolimit (actions: discover, catalog, seller, flows)
skillNoskill (actions: flows)
stateNostate (actions: seller)
venueNoa venue id (x402-base, x402-solana, x402-arbitrum, x402-robinhood, x402-monad, memoacp-base, erc8183-base, bitagent-base) or a marketplace id (actions: venues, outlets)
actionNowhat to do (default discover): discover | match | suggest | catalog | skills | seller | venues | landscape | search | outlets | prices | compare | book | listings | flows | readinessdiscover
offsetNooffset (actions: catalog)
paramsNooperation parameters, e.g. { "vault": "vault:tenant:tenant-3" } (actions: prices, compare, book, listings)
sellerNo0x… seller (optional) (actions: suggest, seller)
sourceNosource (actions: flows)
statusNostatus (actions: catalog, skills)
tenantNotenant (actions: readiness)
api_keyNoapi key (actions: suggest, search, outlets, prices, compare, book, listings)
classesNoclass ids of the class language, when known (they skip the classify step) (actions: outlets)
summaryNosummary (actions: readiness)
agent_idNothe ERC-8004 agentId (decimal), or a seller address (0x…) (actions: readiness)
chain_idNochain id (actions: suggest, readiness)
findingsNoanswer the findings with their records instead of the profile (actions: seller)
hireableNohireable (actions: discover)
protocolNomcp, a2a, uagents, n8n, x402 (actions: catalog)
verticalNoone vertical or several, comma-separated: classes, venues, agents, ops, programs, strategies; markets and routes with a key (actions: search)
price_usdNothe seller's own price per call in USD (actions: outlets)
budget_usdcNobudget usdc (actions: match)
typesafe_keyNotypesafe key (actions: suggest)
required_skillsNorequired skills (actions: match)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"what to do (default discover): discover | match | suggest | catalog | skills | seller | venues | landscape | prices | compare | book | listings | flows | readiness"New value: +"what to do (default discover): discover | match | suggest | catalog | skills | seller | venues | landscape | search | outlets | prices | compare | book | listings | flows | readiness"
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "discover",
      -  "match",
      -  "suggest",
      -  "catalog",
      -  "skills",
      -  "seller",
      -  "venues",
      -  "landscape",
      -  "prices",
      -  "compare",
      -  "book",
      -  "listings",
      -  "flows",
      -  "readiness"
      -]New value: +[
      +  "discover",
      +  "match",
      +  "suggest",
      +  "catalog",
      +  "skills",
      +  "seller",
      +  "venues",
      +  "landscape",
      +  "search",
      +  "outlets",
      +  "prices",
      +  "compare",
      +  "book",
      +  "listings",
      +  "flows",
      +  "readiness"
      +]
    • changedInput schema / properties / api_key / description
      Previous value: -"api key (actions: suggest, prices, compare, book, listings)"New value: +"api key (actions: suggest, search, outlets, prices, compare, book, listings)"
    • addedInput schema / properties / classes
      Added value: +{
      +  "description": "class ids of the class language, when known (they skip the classify step) (actions: outlets)",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / facet
      Added value: +{
      +  "description": "optional: count every match by this attribute before the cut (the answer adds total and facets) (actions: search)",
      +  "enum": [
      +    "venue",
      +    "cohort",
      +    "class",
      +    "vertical"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / mode
      Added value: +{
      +  "description": "default hybrid: words and meaning fused (actions: search)",
      +  "enum": [
      +    "hybrid",
      +    "text",
      +    "vector"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / need
      Added value: +{
      +  "description": "what you sell, in plain words (or send classes) (actions: outlets)",
      +  "type": "string"
      +}
    • addedInput schema / properties / price_usd
      Added value: +{
      +  "description": "the seller's own price per call in USD (actions: outlets)",
      +  "minimum": 0,
      +  "type": "number"
      +}
    • changedInput schema / properties / q / description
      Previous value: -"words for the work, e.g. \"market data\", \"copy trading\", \"strategy backtest\" (actions: discover, catalog)"New value: +"words for the work, e.g. \"market data\", \"copy trading\", \"strategy backtest\" (actions: discover, catalog, search)"
    • addedInput schema / properties / top
      Added value: +{
      +  "description": "rows to return (default 10) (actions: search)",
      +  "maximum": 25,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedInput schema / properties / venue / description
      Previous value: -"a venue id (x402-base, x402-solana, x402-arbitrum, x402-robinhood, x402-monad, memoacp-base, erc8183-base, bitagent-base) or a marketplace id (actions: venues)"New value: +"a venue id (x402-base, x402-solana, x402-arbitrum, x402-robinhood, x402-monad, memoacp-base, erc8183-base, bitagent-base) or a marketplace id (actions: venues, outlets)"
    • addedInput schema / properties / vertical
      Added value: +{
      +  "description": "one vertical or several, comma-separated: classes, venues, agents, ops, programs, strategies; markets and routes with a key (actions: search)",
      +  "type": "string"
      +}
  2. Changed4 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"what to do (default discover): discover | match | suggest | catalog | skills | seller | venues | landscape | flows | readiness"New value: +"what to do (default discover): discover | match | suggest | catalog | skills | seller | venues | landscape | prices | compare | book | listings | flows | readiness"
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "discover",
      -  "match",
      -  "suggest",
      -  "catalog",
      -  "skills",
      -  "seller",
      -  "venues",
      -  "landscape",
      -  "flows",
      -  "readiness"
      -]New value: +[
      +  "discover",
      +  "match",
      +  "suggest",
      +  "catalog",
      +  "skills",
      +  "seller",
      +  "venues",
      +  "landscape",
      +  "prices",
      +  "compare",
      +  "book",
      +  "listings",
      +  "flows",
      +  "readiness"
      +]
    • changedInput schema / properties / api_key / description
      Previous value: -"api key (actions: suggest)"New value: +"api key (actions: suggest, prices, compare, book, listings)"
    • addedInput schema / properties / params
      Added value: +{
      +  "description": "operation parameters, e.g. { \"vault\": \"vault:tenant:tenant-3\" } (actions: prices, compare, book, listings)",
      +  "type": "object"
      +}
  3. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare openWorldHint=true, readOnlyHint=false and idempotentHint=false, and the description adds real context beyond them: which actions need a live key (book, the keyed vertical search), that prices follow a stated undercut rule, and that facet adds total/facets to the answer. It never explains why a 'Finds' tool is not read-only, nor whether calls incur cost or side effects, which is the main behavioral question here.

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?

The routing sentence is correctly front-loaded, but the action catalogue is one dense run-on with em-dashes and no line breaks, making 16 actions hard to scan. Length is partly justified by the tool's breadth, but the format costs more than the words do.

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?

For a 16-action, 33-parameter tool with no output schema, the description covers action intent well but says almost nothing about return shape beyond 'ranked' and 'each row with what to read and the next call'. The mismatch between the read-flavoured name and readOnlyHint=false is left unexplained, which is the largest remaining gap.

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% and every parameter already names its actions, so the baseline is 3. The description goes further by giving semantics the schema lacks: the undercut pricing rule, what facets do to the result, that classes skip the classify step, and concrete venue ids. Given 33 parameters, though, most individual params are only echoed by name.

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?

Opens with a specific verb and resource: 'Finds agents, capabilities and resold skills for a job, ranked', then enumerates all 16 actions with a distinct scope for each. It explicitly separates itself from taifoon_hire and taifoon_demand, so an agent can route 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?

The second sentence gives explicit routing: use taifoon_hire to hire the one you found, taifoon_demand to post a need. Each action also carries a short when-to-use clause (discover for words, match for required_skills, compare by class, listings by path/classes). What is missing is any exclusion guidance between similar actions, e.g. discover vs search vs catalog, which overlap heavily.

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