Skip to main content
Glama

Buyer questions and AI answers

get_prompts
Read-only

The buyer questions (prompts) tracked for the brand and the real AI answers to them. view: tracked = tracked questions with visibility and who is named; gaps = questions where a competitor is named and the brand is not; answers = real AI answer excerpts, filter with query / prompt; fanout = web searches the AI ran behind each question; suggestions = questions worth tracking (adds nothing, 20 calls a day). Read-only. Replies with metrics carry glossary: the dashboard's own explanation of each one.

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": "get_prompts"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoOnly for view tracked, gaps, answers, fanout. End date YYYY-MM-DD. Default: now.
fromNoOnly for view tracked, gaps, answers, fanout. Start date YYYY-MM-DD. Default: all time.
viewNoWhat to return (default tracked).
brandNoBrand id, name or domain (from get_account (view: brands)). Optional when the account has a single brand.
countNoOnly for view suggestions. How many AI suggestions (default 10, max 25).
limitNoOnly for view tracked, gaps, answers, fanout. Max items to return (the default and the maximum depend on the view; a larger value is capped).
queryNoOnly for view answers. Optional text to search in the question or the answer.
engineNoOnly for view tracked, gaps, answers, fanout. Optional AI engine filter, comma separated: chatgpt, gemini, perplexity, ai_overviews, ai_mode. Default: all engines.
offsetNoOnly for view tracked, gaps, answers. Items to skip, for pagination.
promptNoOnly for view answers. Optional text the tracked prompt must contain.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so 'Read-only' in the description adds nothing. It does contribute a real behavioral fact beyond the annotations — the 20-calls-a-day cost of the suggestions view — and notes that metric replies carry a glossary. It says nothing about result caps or pagination consequences in prose (the cap note lives only in the schema).

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 resource statement, then a compact semicolon-delimited view menu — efficient, and the trailing glossary note is worth its space. It is a single dense paragraph, however, and the run-on view enumeration would scan faster as a structured list.

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?

For a 10-parameter, zero-required read tool with no output schema, the description covers purpose, view selection, the one usage-cost trap, and the shape of the response (metrics plus glossary). Remaining details — pagination semantics, per-view default/max limits, brand resolution — are adequately carried by the schema and the get_account reference.

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 a 3 is the baseline, but the description earns a notch more: it explains what each view actually returns, points out that answers can be filtered with query/prompt, and flags that suggestions uses a separate count control rather than limit. That meaning is not derivable from the schema's terse 'What to return' enum 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 resource precisely — tracked buyer questions (prompts) and the real AI answers — and enumerates the five views, so an agent knows exactly what comes back. It stops short of naming or contrasting any sibling tool (e.g. get_visibility, get_content), and the phrasing is nominal rather than verb-led, so it does not fully meet the sibling-differentiation bar for a 5.

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 view enumeration functions as explicit routing: tracked for visibility and who is named, gaps for competitor-named/brand-absent, answers for excerpts with query/prompt filters, fanout for the underlying web searches, suggestions for expansion candidates. It also warns that suggestions 'adds nothing' and costs 20 calls a day. The only gap is guidance on when to use this tool rather than a sibling metrics tool.

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.