extractExtract structured data (entities, fields, records) from unstructured text into JSON. Price: 0.05 USDC per call (x402, Base). Resource: https://api.exo-trust.com/execute/extract. Returns the payment challenge unless already settled.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| fields | No | ||
| schema | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It usefully discloses the price per call, the resource URL, and the payment-challenge return behavior. However, it does not mention authentication, rate limits, data handling, failure modes, or the JSON structure returned beyond the payment challenge.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: purpose is front-loaded, followed by pricing/resource details, then payment behavior. Every sentence provides necessary information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a paid external API with no output schema and no annotations, the description is incomplete. It covers payment and broad output format but omits parameter semantics, authentication, error behavior, and the structure of the returned JSON. An agent could not confidently construct a correct 'schema' argument or anticipate failures.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate, but it never explains the 'fields' or 'schema' parameters. The phrase 'entities, fields, records' weakly hints at the 'fields' parameter, but there is no guidance on how to specify the schema object or what field values should look like.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb and resource: extracting structured data (entities, fields, records) from unstructured text into JSON. This naturally distinguishes it from sibling text-processing tools like summarize, translate, rewrite, or classify, which do not produce structured extractions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The core use case is implied by the description: use this tool when you need structured data from unstructured text. However, there is no explicit guidance about when not to use it or how it compares with siblings such as classify or summarize, so usage guidance is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes, but edgar_financials and edgar_report overlap heavily, with the report apparently building on the same financial data. The three registry lookups (sanctions, VAT, LEI) are distinct, and the text-processing tools are separable.
Naming is inconsistent: some tools use bare verbs (classify, extract, proofread, rewrite, summarize, translate), some use verb_noun (check_sanctions, lookup_lei, validate_vat, code_explain), and others use domain-based names (clinical_dd, edgar_financials, edgar_report, synergy_discovery). No single consistent convention is applied.
14 tools is within the reasonable range and each covers a distinct specialist area, but the set feels slightly broad and includes a few near-duplicates (edgar_financials vs edgar_report). It is not excessive, though tightening could improve focus.
The catalog covers a wide range of domains: sanctions, VAT, LEI, SEC filings, clinical trials, code analysis, text transformation, and discovery. It includes a discovery tool to enumerate specialists, which helps. Minor gaps like missing update/delete-style operations are not expected for a read-only specialist API, so coverage is strong.