Skip to main content
Glama

Visibility Genies

Read a saved result

read_saved_result
Read-only

Reads a saved result of a paid tool call again, a page at a time: a result cut short to fit your context is read to the end here, never bought again. An answer that fits one page comes back whole; a bigger one a page of its largest list at a time, with the rest of the answer beside it. Uses no credits.

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": {
      "projectId": "<projectId>",
      "resultId": "<resultId>"
    },
    "name": "read_saved_result"
  }
}

Input Schema

NameRequiredDescriptionDefault
listNoThe list to read a page of, by its path in the answer, e.g. "reviews" or "backlinks.rows". Defaults to the largest list when the whole answer does not fit one page. Each page names the lists the answer holds outside its rows; a list inside a row, such as "results[2].items", is read by its path too.
limitNoAt most this many rows. A page also ends at about 20,000 characters.
offsetNoThe row to start from. Defaults to 0; each page says where the next one starts.
resultIdYesThe saved result to read: a resultId from list_saved_results, or the savedResultId a paid tool's answer carries.
projectIdYesRequired. The Visibility Genies project this call works in and is billed to. Call list_projects to find one.

Output Schema

NameRequiredDescriptionDefault
listYes
metaNo
rowsYes
listsYes
answerYes
offsetYes
resultYes
totalRowsYes
nextOffsetYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already establish readOnly/non-destructive, so the description correctly spends its words elsewhere: it discloses the cost model (no credits consumed), the paging mechanics (one page of the largest list at a time, rest of the answer alongside), and that small answers return whole. These are traits an agent cannot infer from the annotation block.

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 cost benefit, and every clause carries information. The colon-chained construction ('again, a page at a time: ... never bought again') is slightly dense and requires a second read, costing it a point.

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, a fully documented five-parameter schema, and annotations covering the safety profile, the description covers the remaining gaps: why to re-read, what it costs, and how paging behaves. Nothing an agent needs to invoke this correctly 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 coverage is 100%, so the baseline is 3, and the description still adds meaning: it explains that paging defaults to the largest list and that the remainder of the answer accompanies each page, which contextualizes why list/offset/limit exist. It does not restate the per-parameter syntax, which the schema already handles.

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?

States a specific verb and resource ('Reads a saved result of a paid tool call again') plus the paging behavior, which distinguishes it from list_saved_results and the many get_saved_* siblings that fetch fresh data. An agent can tell this is a re-read of already-purchased output 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?

Gives a clear triggering condition ('a result cut short to fit your context is read to the end here') and a strong reason to prefer it over re-calling a paid tool ('never bought again', 'Uses no credits'). It does not name a sibling alternative or state exclusions explicitly, so it falls short of full when/when-not guidance.

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