Skip to main content
Glama

Price rereading the site

business_read_quote
Read-only

The price of reading the business again from the web, before anything is spent: a fresh read of its site or channel address and its pages, the same careful read setup made, on the owner's tokens. price: measured, from what this business's last read cost (or, with none, the median read on Marsell), charged at what the read really uses, so say it as about that many tokens; null when nothing measured it, so say no price is known. waiting: a review of the business is already open or reading, so it cannot start; say where. Say the price to the owner and ask; start it with business_read_start only once they say yes, in their next message.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "business_read_quote"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectNoThe project's id or exact name. Optional when the account has one project.

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?

Beyond the readOnlyHint/non-destructive annotations, the description discloses that the cost is charged against the owner's tokens, how the price is derived (this business's last read cost, otherwise a median), and that it is 'about' that many tokens rather than exact. It also documents the null case ('no price is known') and the blocked case ('waiting: a review is already open or reading'). The only gap is that it never says whether the quote itself consumes tokens or how long a quote stays valid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The price semantics are front-loaded, which is good, but the whole definition is one long run-on paragraph mixing return-field semantics, pricing derivation, and call sequencing. Opaque load-bearing terms ('Marsell', 'say no price is known', 'say where') force re-reading instead of being quickly scannable. It is dense rather than wasteful, but structure could be much better.

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 correctly carries the burden of explaining what comes back: a price value with its derivation and null case, and a waiting state with a reason to report. Combined with the approvals workflow and the token-charging note, an agent has enough to call it and relay the result correctly. The unexplained reference to 'the median read on Marsell' is the one piece of context left dangling.

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?

Schema description coverage is 100% and there is a single optional 'project' parameter already documented in the schema, so the baseline of 3 applies. The description refers to 'this business' without tying that to the project identifier or explaining behavior when the account has multiple projects. It adds no meaning beyond the schema for the parameter.

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 a specific verb-resource pair: it returns the price of reading a business's site/channel again from the web, before anything is spent, and it explicitly does not perform the read. It clearly separates itself from the sibling 'business_read_start', which actually starts the read. The wording is obscured by house vocabulary ('Marsell', 'price', 'waiting' as nouns), so an agent must parse unusual phrasing, but the core purpose is recoverable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the ordering constraint explicitly: call this first to get a price, tell the owner, and only call 'business_read_start' once the owner agrees in their next message. That is a concrete when-to-use rule plus a named alternative and the condition that selects it. The 'before anything is spent' framing also establishes when this tool is appropriate versus starting a read.

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.