Skip to main content
Glama

Agent Data Tools: Full list (every tool as its own definition)

HTML table to JSON: extract tables from HTML

html_table_to_json
Read-only

Extract every table from an HTML fragment into JSON: header cells become keys and each body row an object (or raw arrays when there is no header row), with captions, colspans repeated and entities decoded. Give the HTML itself (up to 500 KB). Use to turn web or email tables into data an agent can sort and compute on; to fetch a page first use extract. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "html": "<html>"
    },
    "name": "html_table_to_json"
  }
}

Input Schema

NameRequiredDescriptionDefault
htmlYesHTML containing one or more <table> elements (up to 500 KB)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=false. The description adds real context beyond them: per-call charge of $0.01, first 25 free, failed calls free, repeats not free (consistent with non-idempotent billing), and the read-or-compute-only nature. It stops short of describing error or partial-failure behavior, which keeps it below a 5.

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?

Output semantics are front-loaded in the first sentence, followed by input format, use case, and pricing. It is dense but mostly earns its sentences; the 500 KB limit appears both in the description and the schema, a minor redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so well by describing key/object mapping, headerless array fallback, colspan handling, and entity decoding. Pricing and size limits are covered; error responses are not, a small residual gap given the simple one-parameter tool.

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?

The only parameter has 100% schema coverage and already states the 500 KB limit and table requirement. The description's 'Give the HTML itself (up to 500 KB)' largely restates the schema, adding only the framing that raw HTML markup, not a URL, is expected.

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 names a specific verb (extract) and resource (tables from an HTML fragment) and specifies the output shape: header cells become keys, body rows become objects, raw arrays when no header exists, plus captions, colspans, and entity decoding. It also routes the agent away from a related path ('to fetch a page first use extract'), so it is distinguishable from siblings without opening the 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?

It states the intended use case ('turn web or email tables into data an agent can sort and compute on') and names a prerequisite alternative ('to fetch a page first use extract'). There is no explicit when-not guidance, but the context is clear enough for correct selection.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.