Skip to main content
Glama

gantt-chart

by io.github.theluckystrike
OverviewDiscussionsAdmin

Load a sheet into this session

sheet_load

Upload data to work on. This hosted endpoint has no filesystem, so instead of a file path you send the data once with sheet_load and then pass its name as path to sheet_info, sheet_read, sheet_query, sheet_stats, sheet_find, sheet_add_column, sheet_convert and sheet_write. Give exactly one of csv (raw text, comma or tab separated), xlsx_base64 (a base64-encoded .xlsx workbook) or url. url: fetch a public file instead of pasting base64 (recommended above about 10 KB): the url is fetched here with a 10 second timeout, at most 3 redirects, public http(s) hosts only, and a 2 MB cap, and a fetched file is stored as an .xlsx when it carries the PK zip header and as delimited text otherwise. Loaded sheets are kept for your token and survive between calls; the total is capped at 2 MB per token. Files the other tools write come back as a download link that is valid for one hour.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
csvNoRaw CSV or TSV text, including the header row
urlNourl: fetch a public file instead of pasting base64 (recommended above about 10 KB). Public http(s) only; private, link-local and this endpoint's own zone are refused
nameYesName to refer to this data by: 1-64 characters of letters, digits, underscore or dash, e.g. "sales" or "sales.csv"
xlsx_base64NoBase64-encoded .xlsx workbook

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A5/5.0
Behavior5/5

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

With no annotations provided, the description carries full burden. It discloses the no-filesystem architecture, the storage-per-token model, the 2 MB cap, the url fetch behavior (timeout, redirects, host restrictions, size cap, file-type detection via PK zip header), and that written files return as one-hour download links. All critical side effects and constraints are transparent.

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

Conciseness5/5

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

The description is long but every sentence carries essential information. It is front-loaded with the core purpose, then systematically covers input methods, url details, storage semantics, and the download-link behavior for written files. No redundancy or filler.

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?

Given the tool's complexity (multiple input modes, persistence, interplay with 11 sibling tools, and url fetching rules), the description covers all aspects an agent needs to call it correctly. It explains how loaded data is reused, the constraints on each input, and the retention policy. No output schema is needed for a load operation, and the description is sufficiently complete without it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover 100% of parameters, but the description adds substantial meaning: it explains the mutual exclusivity of csv/xlsx_base64/url, the recommended use of url for large data, and how `name` becomes the `path` argument in all downstream tools. This goes well beyond the schema's per-field descriptions.

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 opens with 'Upload data to work on' and immediately clarifies that this hosted endpoint has no filesystem, so data is sent once and referenced by name as `path` in sibling tools. This precisely distinguishes sheet_load from all read/query/write siblings, which operate on already-loaded sheets.

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 explicitly states 'Give exactly one of csv, xlsx_base64 or url' and provides concrete selection guidance for url (recommended above ~10 KB) with detailed fetch constraints (10s timeout, ≤3 redirects, public http(s) only, 2 MB cap). It also clarifies that loaded sheets persist per token and the total is capped at 2 MB, which tells the agent when to unload or reuse.

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

All gantt-chart 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