Skip to main content
Glama

Tako: Fetch Contents

tako_contents
Read-onlyIdempotent

Fetch the full content behind a url: a web page's text, or an exportable Tako card's data rows. Batch up to 10 urls in one call — each fails on its own.

Fetch only cards that tako_search marked exportable: true. Set max_rows when the recent rows are enough. If a page is long, such as a filing or an annual report, set query to a question to get back only the passages that answer it.

Best for: reading one source in full — a page you need to quote, or the rows behind a card you need to compute over.

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": {
      "urls": "<urls>"
    },
    "name": "tako_contents"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlsYesThe urls to fetch: a Tako card url or a web result url. One call for 8 urls saves 7 round trips.
queryNoWeb pages only: a question the passages should answer. The result holds those passages instead of the page. Omit it to get the whole page.
formatNoTako cards only. `rows` returns the card's data as one table. `card` returns the card's own structure, such as a company card's tabs or a game's box score.
offsetNoTako list cards only: rows to skip. With `max_rows: 1`, it fetches a single row.
premiumNoTako cards only: `true` returns premium cells, shown as 🔒. Charges scale with the rows that hold one, so set it only when the user asks. For one row, pass its own Tako link with `max_rows: 1`. Otherwise set `offset` and `max_rows`.
deliveryNoTako cards only. `inline` returns the data in the result. `link` returns a download link: a CSV file, or a JSON file with `format: "card"`. It expires in 5 minutes. Use `link` when you can run shell commands and want to analyze the data in code. If the download fails, call again inline with `max_rows` at 2,000 or less.
max_rowsNoTako cards only: how many rows to return. Omit it to get up to 2,000 rows. With `delivery: "link"`, you can raise it to 100,000. Charges scale with rows returned, so lower it when the recent rows are enough.
max_charsNoWeb pages only: character cap on the extracted text. Inline fetches default to 100,000 per url, less across a batch. Raise it for a long document; `truncated` reports a cut. With `query`, it caps the passages instead: 100 to 20,000, and 4,000 by default.

Output Schema

NameRequiredDescriptionDefault
usageYesWhat this request cost.
resultsYesOne per requested url, in order.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / premium / description
      Previous value: -"Tako cards only: `true` returns premium cells, which `tako_search` shows as 🔒 and this tool's `note` lists by column. Charges scale with the rows that hold one, so set it only when the user asks, with `max_rows`."New value: +"Tako cards only: `true` returns premium cells, shown as 🔒. Charges scale with the rows that hold one, so set it only when the user asks. For one row, pass its own Tako link with `max_rows: 1`. Otherwise set `offset` and `max_rows`."
  2. Changed1 schema field changed
    • changedInput schema / properties / premium / description
      Previous value: -"Tako cards only: `true` reveals premium cells. `tako_search` shows each one as 🔒, and this tool's `note` names their columns. Tako bills each row with one, so set it only when the user asks, with `max_rows`."New value: +"Tako cards only: `true` returns premium cells, which `tako_search` shows as 🔒 and this tool's `note` lists by column. Charges scale with the rows that hold one, so set it only when the user asks, with `max_rows`."
  3. Changed4 schema fields changed
    • changedInput schema / properties / format / description
      Previous value: -"Tako cards only. `rows` returns the card's data as one table. `card` returns the card's own structure, such as a company card's tabs or a game's box score. A card type without its own structure returns `rows`. Web pages ignore it."New value: +"Tako cards only. `rows` returns the card's data as one table. `card` returns the card's own structure, such as a company card's tabs or a game's box score."
    • changedInput schema / properties / offset / description
      Previous value: -"Tako list cards only: rows to skip. With `max_rows: 1`, it fetches one person's row."New value: +"Tako list cards only: rows to skip. With `max_rows: 1`, it fetches a single row."
    • changedInput schema / properties / premium / description
      Previous value: -"Tako cards only: `true` returns withheld cells, such as a person's email and phone. Tako bills each row with one, so set it only when the user asks."New value: +"Tako cards only: `true` reveals premium cells. `tako_search` shows each one as 🔒, and this tool's `note` names their columns. Tako bills each row with one, so set it only when the user asks, with `max_rows`."
    • changedOutput schema / properties / results / items / properties / note / description
      Previous value: -"Passages or the whole page, a card that fell back to rows, or withheld cells."New value: +"Passages or the whole page, a card that fell back to rows, or premium cells."
  4. Changed3 schema fields changed
    • addedInput schema / properties / offset
      Added value: +{
      +  "description": "Tako list cards only: rows to skip. With `max_rows: 1`, it fetches one person's row.",
      +  "maximum": 100000,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedInput schema / properties / premium
      Added value: +{
      +  "description": "Tako cards only: `true` returns withheld cells, such as a person's email and phone. Tako bills each row with one, so set it only when the user asks.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / results / items / properties / note / description
      Previous value: -"Whether `text` is passages or the whole page, or a card fell back to rows."New value: +"Passages or the whole page, a card that fell back to rows, or withheld cells."
  5. Changed10 schema fields changed
    • addedInput schema / properties / delivery
      Added value: +{
      +  "description": "Tako cards only. `inline` returns the data in the result. `link` returns a download link: a CSV file, or a JSON file with `format: \"card\"`. It expires in 5 minutes. Use `link` when you can run shell commands and want to analyze the data in code. If the download fails, call again inline with `max_rows` at 2,000 or less.",
      +  "enum": [
      +    "inline",
      +    "link"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / format
      Added value: +{
      +  "description": "Tako cards only. `rows` returns the card's data as one table. `card` returns the card's own structure, such as a company card's tabs or a game's box score. A card type without its own structure returns `rows`. Web pages ignore it.",
      +  "enum": [
      +    "rows",
      +    "card"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / max_rows / description
      Previous value: -"Tako cards only: how many rows to return. Omit it for the whole card, up to 2,000 rows. Every row delivered is billed, so lower it when the recent rows are enough."New value: +"Tako cards only: how many rows to return. Omit it to get up to 2,000 rows. With `delivery: \"link\"`, you can raise it to 100,000. Charges scale with rows returned, so lower it when the recent rows are enough."
    • changedInput schema / properties / max_rows / maximum
      Previous value: -2000New value: +100000
    • changedInput schema / properties / urls / description
      Previous value: -"The urls to fetch: a Tako card url or a web result url. One call for 8 urls costs the same as 8 separate calls and saves 7 round trips."New value: +"The urls to fetch: a Tako card url or a web result url. One call for 8 urls saves 7 round trips."
    • addedOutput schema / properties / results / items / properties / card
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "The card's structure.",
      +  "propertyNames": {
      +    "type": "string"
      +  },
      +  "type": "object"
      +}
    • addedOutput schema / properties / results / items / properties / download
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "The file, in link mode.",
      +  "properties": {
      +    "expires_at": {
      +      "type": "string"
      +    },
      +    "file_format": {
      +      "enum": [
      +        "csv",
      +        "json"
      +      ],
      +      "type": "string"
      +    },
      +    "total_rows": {
      +      "description": "Rows behind the card, before `max_rows`.",
      +      "type": "number"
      +    },
      +    "url": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "url",
      +    "expires_at",
      +    "file_format"
      +  ],
      +  "type": "object"
      +}
    • changedOutput schema / properties / results / items / properties / error / description
      Previous value: -"Why this url alone failed; the others are unaffected."New value: +"Why this url failed."
    • changedOutput schema / properties / results / items / properties / note / description
      Previous value: -"Whether `text` holds the passages for `query` or the whole page."New value: +"Whether `text` is passages or the whole page, or a card fell back to rows."
    • changedOutput schema / properties / results / items / properties / text / description
      Previous value: -"Web pages only: the page text, or its passages when `query` is set."New value: +"Web pages only: the page text or its passages."
  6. Changed4 schema fields changed
    • changedInput schema / properties / max_chars / description
      Previous value: -"Web pages only: character cap on the extracted text. Inline fetches default to 100,000 per url, less across a batch. Raise it for a long document; `truncated` reports a cut."New value: +"Web pages only: character cap on the extracted text. Inline fetches default to 100,000 per url, less across a batch. Raise it for a long document; `truncated` reports a cut. With `query`, it caps the passages instead: 100 to 20,000, and 4,000 by default."
    • changedInput schema / properties / query / description
      Previous value: -"Web pages only: return the passages around matches of this phrase instead of the whole page. The full page is always scanned, so no match means the phrase isn't there."New value: +"Web pages only: a question the passages should answer. The result holds those passages instead of the page. Omit it to get the whole page."
    • changedOutput schema / properties / results / items / properties / note / description
      Previous value: -"What the `query` match found."New value: +"Whether `text` holds the passages for `query` or the whole page."
    • changedOutput schema / properties / results / items / properties / text / description
      Previous value: -"Web pages only: the page text."New value: +"Web pages only: the page text, or its passages when `query` is set."
  7. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world, and the description layers on genuinely new behavior: per-url failure isolation in a batch, premium cell charges that scale with rows, the 5-minute expiry on `delivery: link`, the inline char cap and `truncated` flag, and the fallback to inline with `max_rows` ≤ 2,000 if a download fails. That is materially more than the structured fields convey.

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 core action and the batching rule, then organized into a 'Best for' close. It is tight for eight parameters, though a couple of schema points (offset/max_rows slicing) are restated rather than adding new information.

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?

With an output schema present, rich annotations, and 100% parameter coverage, the description covers the only remaining gaps: batch failure semantics, cost implications, link expiry, and truncation reporting. An agent has everything needed to call this correctly on the first attempt.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds decision-level meaning: when to reach for `query` versus a full page, why to lower `max_rows` (cost scales with rows), and the `premium` caveat of passing a single row's own Tako link with `max_rows: 1`. It adds value beyond the schema's already thorough per-parameter text, though a few details (offset+max_rows paging recipe) are repeated rather than extended.

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: 'Fetch the full content behind a url,' then enumerates the two return shapes (web page text vs. Tako card data rows). It also anchors itself against the sibling set by referencing `tako_search` and its `exportable: true` marker, so an agent can distinguish it from search-oriented tools 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?

Usage guidance is concrete: batch up to 10 urls, fetch only cards marked exportable by `tako_search`, use `max_rows` when recent rows suffice, and use `query` for long documents like filings. It gives clear situational context but never states an explicit exclusion or a 'prefer tako_search instead when…' routing rule, so it falls just short of a 5.

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.