Skip to main content
Glama

Read the company text from a file

extract_site_file_text

When the site cannot be read: a saved page (HTML), a PDF or a text file -> its text, to describe the company with suggest_company_description(text=...). Part of a new search's onboarding: the first assistant call of an onboarding spends one brief (a free account has one search brief and may call each assistant once); pass the returned onboarding_id to the next calls and to create_search. [REST: POST /api/assist/site_file]

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": {
      "file_name": "<file_name>",
      "data_base64": "<data_base64>"
    },
    "name": "extract_site_file_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_nameYesThe file's name with its extension.
data_base64YesThe file's bytes, base64.
onboarding_idNoThe onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the same new search.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations only declare safety flags (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description carries real additional weight: it discloses a consumption/quota constraint ('a free account has one search brief and may call each assistant once') and the onboarding_id threading requirement across follow-up assistant calls and create_search. It does not describe failure modes (size limits, unsupported/encrypted PDFs), leaving that gap.

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?

Purpose and trigger are front-loaded in the first clause, and the follow-on sentences cover next-step routing, quota, and id threading without filler. It is dense — the quota parenthetical and the bracketed REST endpoint pack several ideas into one sentence — but every element carries decision-relevant information.

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?

There is no output schema, and the description compensates by stating the return is the file's text and that the first answer also yields an onboarding_id. Together with the quota note, that is nearly everything needed to call it correctly; only error/limit behavior for oversized or malformed files is missing.

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 description coverage is 100%, so the baseline is 3 and the schema already documents file_name, data_base64 and onboarding_id in detail. The description adds meaning beyond that by naming which file kinds are acceptable (HTML, PDF, plain text), which determines what file_name extension is valid, and by stating how the produced text flows into the text= parameter of suggest_company_description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the concrete resource (a saved HTML page, PDF or text file) and the produced artifact ('its text'), plus the immediate consumer ('to describe the company with suggest_company_description(text=...)'). It is not a clean verb-first statement ('Extract text from a file'), which costs a point, but an agent can still tell exactly what the tool yields and where it fits.

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?

The trigger condition is explicit and exclusionary: use this 'when the site cannot be read', i.e. when the agent only has a saved page or document. It also routes forward to suggest_company_description with the text. It stops short of stating what to do with unsupported formats or a failed extraction, so it is clear context without a full when-not branch.

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.

Resources