Skip to main content
Glama

SourceGeek

Create sheet

create_sheet

Save tabular data as a SourceGeek sheet in the user's workspace, where their team can open, share and score it. Provide the full CSV content: a header row followed by one row per record. When the CSV came from a candidate search, also pass that search's searchId so the sheet carries the full candidate details. To add more candidates to a sheet you already created, pass its artifactId: only candidates not yet in it are appended. For candidate sheets, keep the profile URL column so the sheet can be scored. Candidate rows from a search are then enriched in the background from public profiles, which spends the workspace's credits. Returns the sheet id and its URL in SourceGeek.

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": {
      "title": "<title>",
      "csv": "<csv>"
    },
    "name": "create_sheet"
  }
}

Input Schema

NameRequiredDescriptionDefault
csvYesComplete CSV content: a header row followed by one row per record. For candidate sheets, include a profile URL column so the sheet can be scored later.
titleYesTitle for the sheet artifact. When artifactId is set, the existing sheet keeps its title.
searchIdNoThe searchId a candidate search returned. Pass it whenever the csv came from a candidate search — it attaches the full candidate details shown in the sheet's Details view (for a rediscovery search: each candidate's match reason and history).
artifactIdNoAn existing sheet's artifact id. Set it to append the csv's rows to that sheet (skipping candidates it already has) instead of creating a new sheet — e.g. for a broadened or extra search for the same request.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / searchId / description
      Previous value: -"The searchId a candidate search returned. Pass it whenever the csv came from a candidate search — it attaches the full candidate details shown in the sheet's Details view."New value: +"The searchId a candidate search returned. Pass it whenever the csv came from a candidate search — it attaches the full candidate details shown in the sheet's Details view (for a rediscovery search: each candidate's match reason and history)."
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Goes well past the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) by disclosing that candidate rows are 'enriched in the background from public profiles, which spends the workspace's credits' — a real cost side effect — plus append semantics ('only candidates not yet in it are appended') and the return payload (sheet id and URL). It stops short of stating required permissions or whether repeated calls create duplicate sheets.

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?

The opening sentence front-loads the core action and audience, then each following sentence adds a distinct operational fact (CSV shape, searchId, artifactId append, profile URL column, credit cost, return value). Dense but nearly every sentence earns its place; a slight trim of the redundant CSV-shape restatement would help.

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 compensates by naming the return values (sheet id and URL), and it covers the non-obvious risks (background enrichment, credit consumption) and the append-vs-create decision. Modestly more on failure conditions or permissions would make it fully complete for a mutation tool with open-world behavior.

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%, so the schema already explains csv, title, searchId and artifactId. The description mostly restates those semantics ('full CSV content: a header row followed by one row per record', 'pass that search's searchId'), adding workflow motivation rather than new parameter-level detail. Baseline 3 is appropriate.

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?

States a precise verb and resource: 'Save tabular data as a SourceGeek sheet in the user's workspace', and adds what the artifact is for ('team can open, share and score it'). It does not explicitly distinguish itself from sibling creators like create_shortlist or create_rediscovery_shortlist, so the agent must infer which creation tool applies.

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 concrete conditional guidance: pass searchId 'when the CSV came from a candidate search', and pass artifactId to append to an existing sheet 'instead of creating a new sheet'. It also steers toward artifactId for 'a broadened or extra search for the same request'. What's missing is any statement of when to use this tool rather than the sibling shortlist-creation tools.

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