market-pulse

Live agent job listings

pulse_jobs

Read-only

List open job listings collected from the agent-accessible lanes, each with title, organisation, URL, reward and currency, bid count, posting time and status. Use it to find work an agent can take now; use pulse_lanes first if you need to know which lanes are trustworthy. Freshness is tiered by the caller's API key: free sees listings once they are up to 24h old, basic 4h, pro and above can trigger a live refresh, and newer listings are counted in redacted rather than shown. Read-only for the caller, though a keyed call consumes one pull from the daily quota and a pro+ call may refresh the live collection. Returns {tier, count, total, redacted, upgrade, upgradeUrl, listings[]}. Fails with a refusal if the persistent store is unavailable.

Input Schema

TableJSON Schema

Name	Required	Description
`q`	No	Free-text match over title, org and skills.
`lane`	No	Lane slug to restrict to, e.g. "hackernews" or "algora". Omit for every collected lane.
`limit`	No	Max listings to return (default 100, maximum 500).
`status`	No	Listing status; omit for open listings.

Output Schema

TableJSON Schema

Name	Required	Description
`tier`	Yes	Tier the call was served at: free, basic, pro, max or operator.
`count`	Yes	Listings returned.
`total`	Yes	Matching listings visible to this tier.
`listings`	Yes	Listings with lane, title, org, url, reward, bids, posted and status.
`redacted`	Yes	Newer listings hidden by this tier's freshness window.
`upgradeUrl`	No	Pricing URL when listings were redacted, otherwise null.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 4, 2026

changedInput schema / properties / limit / description

Previous value: -"Max listings to return (default 100)."New value: +"Max listings to return (default 100, maximum 500)."

changedInput schema / properties / status / description

Previous value: -"Listing status; omit for any."New value: +"Listing status; omit for open listings."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "count": {
+      "description": "Listings returned.",
+      "type": "integer"
+    },
+    "listings": {
+      "description": "Listings with lane, title, org, url, reward, bids, posted and status.",
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "redacted": {
+      "description": "Newer listings hidden by this tier's freshness window.",
+      "type": "integer"
+    },
+    "tier": {
+      "description": "Tier the call was served at: free, basic, pro, max or operator.",
+      "type": "string"
+    },
+    "total": {
+      "description": "Matching listings visible to this tier.",
+      "type": "integer"
+    },
+    "upgradeUrl": {
+      "description": "Pricing URL when listings were redacted, otherwise null.",
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "tier",
+    "count",
+    "total",
+    "redacted",
+    "listings"
+  ],
+  "type": "object"
+}

First observedSep 30, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the readOnlyHint/destructiveHint=false annotations by disclosing tiered freshness by API key, that a keyed call consumes one pull from a daily quota, that pro+ can trigger a live refresh, and that newer listings are counted as redacted rather than shown. It also states the failure mode (refusal if the persistent store is unavailable), which annotations cannot convey.

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?

Front-loads purpose and output fields before the operational caveats, and every clause carries information an agent would otherwise have to discover. It is a dense, somewhat run-on block that could be split into shorter sentences, but there is no filler.

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?

Covers listing contents, selection guidance, freshness/quota behavior, and failure mode; the explicit return shape is redundant given the output schema but harmless. For a read-only listing tool with several siblings, 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%, so q, lane, limit and status are already fully documented with defaults and constraints. The description adds contextual color (redaction interacts with result counts, lane trust matters) but no syntax or semantic detail the schema lacks. Baseline 3 applies.

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 open job listings collected from the agent-accessible lanes") and enumerates the fields returned, so the agent knows exactly what it gets without opening the schema. It also distinguishes itself from sibling pulse_lanes by positioning that tool as prerequisite for trust context.

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?

Gives explicit when-to-use ("find work an agent can take now") and names the alternative with its qualifying condition ("use pulse_lanes first if you need to know which lanes are trustworthy"). The lane-scoping guidance in the schema is reinforced by the trust framing in the description.

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.