Skip to main content
Glama

FiledProof

by com.filedproof
OverviewDiscussionsAdmin

Search filing evidence

filedproof.search_evidence
Read-onlyIdempotent

Find relevant primary-source passages across a bounded set of SEC filings. Use this for open-ended filing research when you want evidence records with provenance but do not need a claim verdict or a curated answer bundle. Use filedproof.verify_claim for one explicit factual proposition, filedproof.build_evidence_pack for a compact answer-ready bundle, or filedproof.build_timeline when chronology is the main objective. Relevance is not a truth verdict.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qYesResearch question or disclosure topic.
itemNoOptional SEC filing item, such as 1A or 7.
formsNoSEC forms to search. Defaults to 10-K and 10-Q.
limitNoMaximum number of operation-specific evidence or result records to return.
filingsNoMaximum number of filings to inspect for this invocation.
historyNoWhether to use bounded historical SEC submission archives when needed.
sectionNoOptional exact normalized section heading.
identifierYesTicker, CIK, or exact SEC company name.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / filings / description
      Added value: +"Maximum number of filings to inspect for this invocation."
    • addedInput schema / properties / history / description
      Added value: +"Whether to use bounded historical SEC submission archives when needed."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of operation-specific evidence or result records to return."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "Structured FiledProof result with operation-specific evidence, provenance, coverage, and uncertainty fields.",
+  "type": "object"
+}
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear without the description. The description adds useful context: the search is over a 'bounded set' of filings and that relevance is not a truth judgment. It does not contradict any annotation, and the extra caveat enriches behavioral understanding beyond what annotations alone provide.

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?

The description is four sentences with zero waste. The core purpose is front-loaded in the first sentence, followed by same-sentence scoping, then a compact list of alternatives, and a final one-line caveat. Every sentence earns its place, and there is no redundant rephrasing of the tool name or title.

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?

Given an output schema exists (so return format is handled separately) and the schema fully documents all 8 parameters, the description covers the remaining operational context: purpose, scope (bounded set), what it does NOT return, and routing to siblings. Nothing an agent needs to decide when to call it or how to frame a query 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% – every one of the 8 parameters has a detailed description in the schema (e.g., 'Research question or disclosure topic', 'Optional SEC filing item, such as 1A or 7'). The tool description itself adds no per-parameter meaning; it only frames the overall operation. Per the high-coverage baseline, a 3 is appropriate; the description does not need to repeat what the schema already documents.

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 a specific verb and resource: 'Find relevant primary-source passages across a bounded set of SEC filings.' It immediately differentiates itself from siblings by stating it returns 'evidence records with provenance' but not a claim verdict or curated bundle, and it names three alternative tools with distinct purposes. This makes the tool's intent unambiguous and distinct.

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?

Usage guidance is explicit and actionable: it lists exactly when to use this tool versus filedproof.verify_claim, filedproof.build_evidence_pack, and filedproof.build_timeline. It also adds a critical caveat, 'Relevance is not a truth verdict,' which prevents misinterpretation. No agent needs to infer when to call it.

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

All FiledProof toolsInspect
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