market-pulse

Should an agent bid on this lane?

pulse_should_i_bid

Read-onlyIdempotent

Get a one-call, evidence-backed recommendation on whether an autonomous agent should spend attempts on a lane: one of bid, bid_cautiously, probe_first, avoid or insufficient_evidence, with the rationale and caveats. Call pulse_lanes first to get the slug, then call this before committing an agent's time or an application to any lane; it is the decision tool, while pulse_lane_detail is the audit trail behind it. A recommendation reflects observed outcomes inside the snapshot window, never a guarantee, and Unknown means unmeasured rather than failed. Read-only and idempotent. Works without an API key on the free tier. Returns {lane, grade, confidence, freshness, methodologyVersion, recommendation, rationale, caveats[]}. An unknown lane is refused with an error naming it.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`lane`	Yes	Lane slug to judge, exactly as returned in the slug field of pulse_lanes, e.g. "algora".

Output Schema

TableJSON Schema

Name	Required	Description
`lane`	Yes	The lane slug that was judged.
`grade`	Yes	The lane's assay grade.
`caveats`	Yes	Limits on how far the recommendation can be trusted.
`rationale`	Yes	Why, in one sentence.
`recommendation`	Yes	What the evidence supports doing.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 4, 2026

changedInput schema / properties / lane / description

Previous value: -"Lane slug to judge, as returned by pulse_lanes."New value: +"Lane slug to judge, exactly as returned in the slug field of pulse_lanes, e.g. \"algora\"."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "caveats": {
+      "description": "Limits on how far the recommendation can be trusted.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "grade": {
+      "description": "The lane's assay grade.",
+      "type": "string"
+    },
+    "lane": {
+      "description": "The lane slug that was judged.",
+      "type": "string"
+    },
+    "rationale": {
+      "description": "Why, in one sentence.",
+      "type": "string"
+    },
+    "recommendation": {
+      "description": "What the evidence supports doing.",
+      "enum": [
+        "bid",
+        "bid_cautiously",
+        "probe_first",
+        "avoid",
+        "insufficient_evidence"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "lane",
+    "grade",
+    "recommendation",
+    "rationale",
+    "caveats"
+  ],
+  "type": "object"
+}

First observedSep 30, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Adds real behavior beyond the annotations: works without an API key on the free tier, an unknown lane is refused with an error naming it, and the recommendation reflects observed outcomes within the snapshot window rather than a guarantee. Repeating 'Read-only and idempotent' is redundant given readOnlyHint/idempotentHint, and enumerating the return shape is partly redundant with the output schema, so it stops short of 5.

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-loaded with the decision and its output set, then prerequisites, then caveats; each sentence mostly earns its place. The return-shape enumeration duplicates the output schema and the read-only/idempotent line duplicates the annotations, costing a little tightness.

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 the prerequisite chain, the semantics of ambiguous outputs ('Unknown means unmeasured rather than failed'), error behavior, and the non-guarantee framing. With an output schema present, the description does not need to explain return values yet still clarifies their interpretation, so nothing an agent needs is missing.

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?

With a single parameter at 100% schema coverage the baseline is already 3-4, and the description adds the provenance of the value ('the slug, exactly as returned in the slug field of pulse_lanes'), telling the agent where to source it. No format or validity nuance beyond that.

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 ('evidence-backed recommendation on whether an agent should spend attempts on a lane') and enumerates the exact possible outputs. It explicitly differentiates itself from siblings by naming pulse_lanes as the prerequisite and pulse_lane_detail as 'the audit trail behind it', so an agent can route correctly without opening any schema.

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 an explicit ordering rule ('Call pulse_lanes first to get the slug, then call this before committing an agent's time'), names the alternative decision tool and its role, and states the exclusion implicitly by framing this as the decision tool versus detail's audit role. Nothing is left 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.