Skip to main content
Glama

hedwigai

by com.hedwigai
OverviewDiscussionsAdmin

Pick a table out of a workbook

pick_table
Read-onlyIdempotent

One table from a workbook as data, chosen from your own words. Say what you want in prompt the way you would ask for it — 'the drug programs', 'who the competitors are' — and the table whose content that describes is chosen from every table in the workbook, by the headings above it as the document has them; you do not need to know a heading. The answer's table holds columns, rows (cell text in column order) and citations (the footnotes its cells cite, resolved), with confidence; considered is every table and how likely each was. table is null when none is what you asked for — read considered, or ask again in other words. Omit prompt to list the tables instead: heading path, columns and row count. Reads only; no run starts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sheetNoOne tab's id, to look only in that tab.
promptNoWhat table you want, in your own words. Omit to list the tables.
contextNoExplain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
versionNoAn earlier version to read instead of the current one.
workbookYesThe workbook id.
llm_modelNoThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / context
      Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}
    • addedInput schema / properties / llm_model
      Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent and non-destructive safety, yet the description adds genuinely new behavior: the null-table fallback when nothing matches, the presence of a `considered` ranking and `confidence` score, citation resolution, and that no run starts. 'Reads only' partly restates readOnlyHint, which keeps it from a 5.

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 core purpose and prompt semantics are front-loaded, and every sentence (output shape, null case, listing mode, read-only) carries information. The em-dash-heavy prose is dense and slightly run-on, but it is appropriately sized for the tool's complexity.

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 six parameters and no output schema, the description carries the return-value burden and does so fully: it describes `table` (columns, rows, citations, confidence), `considered`, the null case, and the alternate listing output. Nothing an agent needs to invoke and interpret it 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; the description goes beyond it by explaining `prompt` as free-form natural language with examples and by spelling out that omitting it switches the tool to a listing mode. It adds no meaning for `sheet`, `version`, `context` or `llm_model`, which the schema already documents.

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?

The description states a specific verb and resource ('One table from a workbook as data, chosen from your own words') and defines the selection mechanism (semantic match over headings). It is clearly distinguishable from siblings like pick_section and read_workbook without opening any 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?

It gives clear context for use ('say what you want in prompt... you do not need to know a heading') and a secondary mode ('Omit prompt to list the tables instead'), plus recovery advice when no match is found. It stops short of explicitly naming alternative sibling tools such as pick_section for the same job, so it is clear but not fully routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All hedwigai toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources