Skip to main content
Glama
Sign In

SheetsData

by io.github.octoco-ltd
OverviewDiscussionsAdmin

Read Datasheet

read_datasheet
Read-only

Costs 2¢ per call. Reads a part's datasheet. Section mode (default): start with section='summary' for an overview and available_sections, then ask for any section by name; names come from the datasheet's own headings (e.g. 'register_map', 'i2c_interface'); an unknown name returns the nearest section names and pages. Use max_chars and the returned next_offset to continue a long read. Search mode (mode='search' with a query): semantic search within this datasheet, for targeted questions such as a register bit field or an I2C address. Prefer specific sections to section='all', which can fill your context. The first read of a new part starts extraction and returns status='extracting' (not charged). A new datasheet takes about 2.5 minutes at the median and 6.5 minutes at the 90th percentile; a cold GPU start can take about 12 minutes. These are estimates, not deadlines. For microcontrollers, register-level programming detail usually lives in a separate reference manual, not the datasheet; available_sections shows what is present. datasheet_status: 'ready' → read it; 'extracting' / 'queued' / 'pending' / 'resolving' → poll check_extraction_status; 'not_extracted' → prefetch_datasheets; 'no_source' / 'unsupported' → request_datasheet_upload. Full list in the server instructions.

Input Schema

NameRequiredDescriptionDefault
modeNo'section' (default) returns a named section, 'search' does semantic searchsection
limitNoMax search results in search mode (default 3). Each result includes adjacent context chunks.
queryNoSearch query; required when mode='search', ignored otherwise. Example: 'charge voltage register', 'I2C address'.
formatNoFor a named section, json returns tables as columns and rows plus remaining text, preserving source cells (useful for register_map). Paging and page citations still apply.markdown
offsetNoContinue a section using next_offset from the previous read.
sectionNoSection name for section mode. Start with 'summary' to discover available sections. Common: summary, pinout, electrical, abs_max, register_map, timing, package. Any heading in the datasheet works (slugified).summary
max_charsNoText budget; a whole sentence or table row may exceed it.
part_numberYesSpecific manufacturer part number (MPN) or LCSC number (e.g. 'TPS54302DDCR', 'C2837938'). Not a value ('100nF'), description or reference designator ('R1').

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / format
      Added value: +{
+  "default": "markdown",
+  "description": "For a named section, json returns tables as columns and rows plus remaining text, preserving source cells (useful for register_map). Paging and page citations still apply.",
+  "enum": [
+    "markdown",
+    "json"
+  ],
+  "type": "string"
+}
  2. Changed4 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Max search results for search mode (default 3). Each result includes adjacent context chunks for continuity."New value: +"Max search results in search mode (default 3). Each result includes adjacent context chunks."
    • changedInput schema / properties / mode / description
      Previous value: -"Reading mode: 'section' (default) returns a named section, 'search' does semantic search"New value: +"'section' (default) returns a named section, 'search' does semantic search"
    • changedInput schema / properties / part_number / description
      Previous value: -"Specific manufacturer part number (MPN) or LCSC number. Not a value or description."New value: +"Specific manufacturer part number (MPN) or LCSC number (e.g. 'TPS54302DDCR', 'C2837938'). Not a value ('100nF'), description or reference designator ('R1')."
    • changedInput schema / properties / query / description
      Previous value: -"Search query — REQUIRED when mode='search', ignored when mode='section'. Example: 'charge voltage register', 'I2C address'."New value: +"Search query; required when mode='search', ignored otherwise. Example: 'charge voltage register', 'I2C address'."
  3. Changed4 schema fields changed
    • changedInput schema / properties / limit / default
      Previous value: -10New value: +3
    • changedInput schema / properties / limit / description
      Previous value: -"Max search results for search mode (default 10). Each result includes adjacent context chunks for continuity."New value: +"Max search results for search mode (default 3). Each result includes adjacent context chunks for continuity."
    • addedInput schema / properties / max_chars
      Added value: +{
+  "description": "Text budget; a whole sentence or table row may exceed it.",
+  "maximum": 60000,
+  "minimum": 500,
+  "type": "integer"
+}
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Continue a section using next_offset from the previous read.",
+  "minimum": 0,
+  "type": "integer"
+}
  4. Changed1 schema field changed
    • changedInput schema / properties / query / description
      Previous value: -"Search query for search mode (e.g. 'charge voltage register', 'I2C address')"New value: +"Search query — REQUIRED when mode='search', ignored when mode='section'. Example: 'charge voltage register', 'I2C address'."
  5. Changed2 schema fields changed
    • changedInput schema / properties / limit / default
      Previous value: -5New value: +10
    • changedInput schema / properties / limit / description
      Previous value: -"Max search results for search mode (default 5)"New value: +"Max search results for search mode (default 10). Each result includes adjacent context chunks for continuity."
  6. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only declare readOnly/openWorld/non-destructive; the description adds real behavioral context the annotations cannot: 2¢ per call cost, that the first extraction read is not charged, and concrete latency estimates (2.5 min median, ~12 min cold GPU). It also warns that microcontroller register detail may live in a separate reference manual. Only minor gap: no explicit statement about auth or rate limits.

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 cost and the core section-mode workflow, then search mode, then status routing. Long but dense and largely waste-free; the status-mapping sentence is a slight compression win but adds length rather than cutting it.

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?

For an 8-parameter, no-output-schema tool, the description covers mode selection, paging, cost, latency, failure states, and sibling routing – everything an agent needs to call it correctly and interpret the result.

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% (baseline 3), but the description still adds non-duplicative meaning: section names derive from the datasheet's own slugified headings, unknown names return nearest sections and pages, and next_offset/max_chars are framed as a paging workflow. This goes beyond the schema's field-level text.

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+resource ('Reads a part's datasheet') and immediately distinguishes its two operating modes (section vs. search) with concrete examples of section names and queries. An agent can identify what this tool does 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: start with section='summary', prefer named sections over 'all' which 'can fill your context', and maps each datasheet_status value to the correct alternative sibling (check_extraction_status, prefetch_datasheets, request_datasheet_upload). This is a full when/when-not/alternative map.

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

All SheetsData toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources