Extract clean text and metadata from supplied PDF, DOCX, HTML, Markdown, CSV, JSON, YAML, or plain-text documents.
| Name | Required | Description | Default |
|---|---|---|---|
| filename | Yes | ||
| content_base64 | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | Structured Document extraction result | |
| meta | Yes | ||
| service | Yes | ||
| version | Yes | ||
| request_id | Yes | Unique request identifier |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description adds that the tool outputs 'clean text and metadata' and lists supported formats, but does not disclose additional limitations or behavioral details beyond that.
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 a single concise sentence, front-loading the core function and listing supported formats efficiently without wasted words. Every word contributes to the purpose.
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?
The tool has only 2 required params, an output schema exists, and annotations cover safety, so the description needn't explain return values or safety. It adequately covers purpose and supported formats, though it could mention the need for base64 encoding and format-specific caveats. Overall, it is sufficiently complete for the tool's complexity.
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. It lists supported document formats but does not explain that content_base64 is the Base64-encoded file content, nor does it clarify the relationship between filename and content. The parameter names are self-explanatory but the description adds minimal semantic detail beyond the schema.
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 the tool extracts clean text and metadata from a specific list of document formats, using the verb 'extract' and naming the resource. It distinguishes itself from siblings like web.extract by focusing on supplied documents rather than web URLs.
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 description implies this tool is for extracting text/metadata from supplied files, but it does not explicitly state when to use it vs alternatives like web.extract or document.tables. No exclusions or conditional recommendations are provided.
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.
Tools are grouped into clear domain prefixes (crypto, data, developer, document, research, web) and each tool name describes a specific function; however, a few umbrella tools like web.full-audit and data.contract overlap with their more targeted counterparts, creating minor ambiguity.
All tool names follow a consistent pattern: a domain prefix, a dot, and a hyphenated lowercase compound name (e.g., crypto.base-block-inspect, web.seo-audit). This makes naming predictable and easy to scan.
At 63 tools, the surface area is very large and exceeds the 50+ threshold for extreme mismatch. While the tools are organized into six domains, the sheer number makes it difficult for an agent to select efficiently, and some tools are bundled combinations of others.
Each domain offers a thorough set of operations: crypto covers address, account, block, contract, events, gas, and transaction inspection; data covers cleaning, conversion, schema, and validation; developer covers code review, dependency/license audits, and test generation; research covers SEC, OFAC, GLEIF, and USAspending; web covers extraction, SEO, security, and performance. No obvious dead ends exist for the read-only/inspection purpose.