Perq

Find free credits for a need

find_credits

Read-onlyIdempotent

Answer "what free credits / free tier / startup program can I get for X". Ranked, verified offers matching a need such as "free speech to text credits", "GPU for a bootstrapped startup" or "student LLM API credits". Each result has credit_value, eligibility, how_to_claim, claim_url, source_url, source_snippet (verbatim vendor quote), last_verified, value_usd (explicit one-time USD amount or null), audience, and live claims / claims_7d / votes counts (real visitors, never padded; null if unavailable). filters.sort orders by relevance (default), popular (most claimed this week), votes, newest, verified (most recently re-checked), value (largest stated USD credit) or az. need may be empty when you only filter/sort. Closed offers are excluded unless filters.status is "all"/"closed" or include_closed is true. claim_redirect_url sends the user to the vendor and counts the claim anonymously; claim_url is the direct vendor link.

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": "find_credits"
  }
}

Input Schema

Name	Required	Description	Default
`need`	No	What the user wants credits for, in plain words. E.g. "speech to text", "GPU compute for a bootstrapped startup", "vector database". May be empty ("") to list by filters and sort only.
`filters`	No	Optional filters.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 22, 2026

addedInput schema / properties / filters / properties / audience

Added value: +{
+  "description": "Who can claim: startup, student, anyone, members (members = customers of a bank/marketplace partner). Comma-separate to require several.",
+  "type": "string"
+}

addedInput schema / properties / filters / properties / min_value

Added value: +{
+  "description": "Only offers whose credit_value leads with an explicit one-time USD amount of at least this much (e.g. 10000).",
+  "type": "number"
+}

addedInput schema / properties / filters / properties / sort

Added value: +{
+  "description": "relevance (default), popular, votes, newest, verified, value, az.",
+  "enum": [
+    "relevance",
+    "popular",
+    "votes",
+    "newest",
+    "verified",
+    "value",
+    "az"
+  ],
+  "type": "string"
+}

addedInput schema / properties / filters / properties / status

Added value: +{
+  "description": "live (default), closed, or all.",
+  "enum": [
+    "live",
+    "closed",
+    "all"
+  ],
+  "type": "string"
+}

changedInput schema / properties / need / description

Previous value: -"What the user wants credits for, in plain words. E.g. \"speech to text\", \"GPU compute for a bootstrapped startup\", \"vector database\"."New value: +"What the user wants credits for, in plain words. E.g. \"speech to text\", \"GPU compute for a bootstrapped startup\", \"vector database\". May be empty (\"\") to list by filters and sort only."

removedInput schema / required
```
Removed value: -[
-  "need"
-]
```

First observedOct 20, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Even though annotations already declare readOnly/idempotent/non-destructive, the description adds substantive behavior beyond them: closed offers are excluded by default, claim counts are "real visitors, never padded; null if unavailable," value_usd is an explicit one-time USD amount or null, and claim_redirect_url sends the user to the vendor and records an anonymous claim. These null-semantics and default-exclusion rules are exactly the kind of context annotations cannot carry.

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?

The key question and scope are front-loaded in the first sentence, and the dense field enumeration is justified because there is no output schema. The middle run of field names is long and could be grouped more tightly, costing one point, but no sentence is pure 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?

With no output schema, the description supplies the return shape (credit_value, eligibility, how_to_claim, claim_url, source_url, last_verified, value_usd, audience, claim counts), the default behaviors (closed offers excluded, relevance sort), and the entry point for claiming. For a zero-required-parameter discovery tool, nothing an agent needs to call it correctly 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?

Schema coverage is 100%, so baseline is 3, but the description adds meaning the schema does not: sort modes are glossed ("popular (most claimed this week)", "value (largest stated USD credit)", "verified (most recently re-checked)") and it clarifies that need is plain-words input. That is genuine value on top of the enum list.

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?

The description opens with the exact user question it answers ("what free credits / free tier / startup program can I get for X") and follows with concrete example needs, so an agent can immediately tell this is a search/discovery tool for credit offers. It is clearly distinct from siblings like get_offer (single lookup), trending, and early_offers, which imply different selection semantics.

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?

It states when need can be empty ("need may be empty when you only filter/sort") and when closed offers enter results (status "all"/"closed" or include_closed true), which are real usage conditions. It also explains claim_redirect_url vs claim_url roles. It stops short of explicitly contrasting against trending/early_offers, so 4 rather than 5.

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

All Perq 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.