Builders in Fintech

Search fintech reports

search_reports

Read-onlyIdempotent

Fintech reports, white papers, surveys and data, newest first, with publisher, type, date and gated flag. Reports are published by the companies, investors, consultancies and analysts named as publisher; we link to the publisher's page and never host the file. Figures are quoted exactly as written, each with page_ref (a page number, or 'web' for an HTML page). gated = registration required at the publisher. Arguments: q (or query, ≥2 characters) matched against title and summary; topic (topic slug); publisher (organisation or person slug); report_type; year; gated (true/false); limit (≤50); cursor (next_cursor from a previous call). Use get_report for figures and coverage. Unknown arguments are rejected.

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": "search_reports"
  }
}

Input Schema

Name	Required	Description
`q`	No	Text matched against report title and summary (at least 2 characters).
`year`	No	Publication year, e.g. 2026.
`gated`	No	true = registration required at the publisher; false = free to read.
`limit`	No	Max rows (≤50).
`topic`	No	Topic slug, e.g. 'stablecoins'.
`cursor`	No	next_cursor from a previous call.
`publisher`	No	Publisher slug (organisation or person).
`report_type`	No	survey, market_data, index, white_paper, regulatory_analysis or industry_research.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description still adds useful behavior: results are newest-first, the file is never hosted (only linked), figures carry page_ref values, gated means publisher registration, and unknown arguments are rejected. That is real added context beyond the annotations, though return-shape detail per row remains thin.

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 resource and result content, then behavior details, then the argument list; there is little filler. The trailing argument enumeration largely duplicates a fully documented schema, which is mild redundancy rather than a defect.

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?

There is no output schema, so the description must convey return content, which it does (publisher, type, date, gated flag, page_ref), along with pagination via cursor/next_cursor and the ≤50 limit. For a read-only search tool with well-documented parameters, an agent has everything needed to call it correctly.

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 coverage is 100%, so all eight parameters are already documented, which sets the baseline at 3. The description adds one genuinely new fact not in the schema — that 'query' is accepted as an alias for q with a ≥2 character minimum — but otherwise mostly restates the schema's own parameter descriptions.

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 ('Fintech reports, white papers, surveys and data') and states the result shape and sort order ('newest first, with publisher, type, date and gated flag'). It also names the sibling to use for a different job ('Use get_report for figures and coverage'), so an agent can separate the two without opening either 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?

Gives a clear positive context (search reports by text, topic, publisher, type, year, gated status) plus an explicit alternative for a different need (get_report for figures and coverage). It stops short of saying when not to use it versus search_content or get_content, but the routing guidance present is concrete.

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

All Builders in Fintech 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.

Resources

Need Help?