market-pulse

List agent-work lanes

pulse_lanes

Read-onlyIdempotent

List the agent-work lanes in the Market Pulse index (bounty boards, agent marketplaces, job feeds, agent networks), each with its evidence-backed grade, liveness, agent-access verdict, freshness and confidence. Use this first to discover lane slugs and to shortlist where an autonomous agent can realistically earn; filters narrow the list and omitting all of them returns every lane. Use pulse_lane_detail for one lane's full record and pulse_should_i_bid for a spend recommendation; use pulse_jobs for individual open listings. Read-only snapshot data, same answer for the same arguments, never changes state. Works without an API key on the free tier. Returns {count, methodologyVersion, lanes[]}; a filter value outside its enum is refused with the values that work, never answered with an empty list.

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": "pulse_lanes"
  }
}

Input Schema

Name	Required	Description
`grade`	No	Assay grade to filter by. A = a received settlement; B = payout evidence short of a received settlement; C = live but payout unproven; F = observed failure; Unknown = insufficient evidence. Omit for every grade.
`access`	No	Whether an agent can reach the lane at all: accessible or blocked. Omit for both.
`category`	No	Lane category, e.g. bounty, agent-marketplace, jobs-feed, agent-network. Free text matched exactly; omit for every category.
`freshness`	No	How recently the lane was observed: fresh (<=24h), aging (<=7d), stale (<=30d), historical (older). Omit for every age.
`automation`	No	What the lane's terms say about automated participation. Omit for every policy.

Output Schema

Name	Required	Description
`count`	Yes	Number of lanes returned.
`lanes`	Yes	Lane summaries: slug, name, category, grade, gradeLabel, liveness, agentAccess, automation, payout, confidence, freshness, lastVerifiedAt, attempts, settlements.
`methodologyVersion`	No	Grading methodology version the grades were produced under.

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedOct 4, 2026

changedInput schema / properties / access / description

Previous value: -"Whether an agent can reach the lane at all: accessible or blocked."New value: +"Whether an agent can reach the lane at all: accessible or blocked. Omit for both."

addedInput schema / properties / access / enum

Added value: +[
+  "accessible",
+  "blocked"
+]

changedInput schema / properties / automation / description

Previous value: -"What the lane's terms say about automated participation."New value: +"What the lane's terms say about automated participation. Omit for every policy."

addedInput schema / properties / automation / enum

Added value: +[
+  "permitted",
+  "silent",
+  "restricted",
+  "unknown"
+]

changedInput schema / properties / category / description

Previous value: -"Lane category, e.g. bounty, agent-marketplace, jobs-feed, agent-network."New value: +"Lane category, e.g. bounty, agent-marketplace, jobs-feed, agent-network. Free text matched exactly; omit for every category."

changedInput schema / properties / freshness / description

Previous value: -"How recently the lane was observed: fresh (<=24h), aging (<=7d), stale (<=30d), historical (older)."New value: +"How recently the lane was observed: fresh (<=24h), aging (<=7d), stale (<=30d), historical (older). Omit for every age."

addedInput schema / properties / freshness / enum

Added value: +[
+  "fresh",
+  "aging",
+  "stale",
+  "historical"
+]

changedInput schema / properties / grade / description

Previous value: -"Assay grade to filter by. A = a received settlement; F = observed failure; Unknown = insufficient evidence."New value: +"Assay grade to filter by. A = a received settlement; B = payout evidence short of a received settlement; C = live but payout unproven; F = observed failure; Unknown = insufficient evidence. Omit for every grade."

addedInput schema / properties / grade / enum

Added value: +[
+  "A",
+  "B",
+  "C",
+  "F",
+  "Unknown"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "count": {
+      "description": "Number of lanes returned.",
+      "type": "integer"
+    },
+    "lanes": {
+      "description": "Lane summaries: slug, name, category, grade, gradeLabel, liveness, agentAccess, automation, payout, confidence, freshness, lastVerifiedAt, attempts, settlements.",
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "methodologyVersion": {
+      "description": "Grading methodology version the grades were produced under.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "count",
+    "lanes"
+  ],
+  "type": "object"
+}

First observedSep 30, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description still adds real behavioral value beyond that: free-tier/no-API-key operation, deterministic answers for identical arguments, the {count, methodologyVersion, lanes[]} return shape, and the specific refusal behavior for out-of-enum filter values. It stops short of describing pagination or result-size limits, which keeps it off a 5.

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?

Dense but front-loaded: purpose and the 'use this first' instruction lead, then routing to alternatives, then behavioral guarantees, then return shape. No sentence is redundant or padded.

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?

With five optional filter parameters, an output schema, and read-only annotations, the description covers everything an agent needs: when to use it, how filters compose, what comes back, and the failure mode for bad enum input. Nothing material is missing.

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% and each parameter (including enum semantics for grade, freshness, automation) is fully documented in the schema itself. The description only adds the aggregate rule that filters narrow the list and omitting all of them returns every lane, which the schema already implies with 'Omit for every grade' style notes. Baseline 3 applies when the schema does the heavy lifting.

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 and resource ('List the agent-work lanes in the Market Pulse index') and enumerates the lane kinds, so the agent knows exactly what domain this covers. It also names three siblings (pulse_lane_detail, pulse_should_i_bid, pulse_jobs) and what each is for, making differentiation immediate.

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?

'Use this first to discover lane slugs and to shortlist where an autonomous agent can realistically earn' gives explicit when-to-use guidance with a stated goal. It also routes to alternatives by name with the condition that selects each, leaving nothing to inference.

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

All market-pulse tools Inspect

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.