Skip to main content
Glama

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 datasheet nobody has read before usually takes 1-3 minutes, 5 or more for a large one or a busy queue. 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

TableJSON 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'.
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. 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'."
  2. 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"
+}
  3. 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'."
  4. 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."
  5. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare read-only/non-destructive, but the description adds substantial behavioral context beyond them: a 2¢ per-call cost, that the first read triggers extraction and is not charged, 1-3 minute (or longer) extraction estimates flagged as estimates not deadlines, and the context-filling risk of section='all'. This is genuine disclosure an agent needs to plan around.

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?

Dense but front-loaded with the cost and the core read behavior before the mode details and status routing. Nearly every sentence carries actionable information, though the status→tool mapping could be compressed since it overlaps with server instructions.

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 a 7-parameter read tool with no output schema, the description covers return-relevant signals (available_sections, next_offset, status='extracting'), continuation mechanics, cost, and failure routing. Nothing an agent needs to invoke it 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, but the description adds real meaning: section names come from the datasheet's own slugified headings, an unknown name returns nearest section names and pages, next_offset drives continuation, and query is only meaningful with mode='search'. 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 and resource ('Reads a part's datasheet') and immediately distinguishes two operating modes (section vs search). An agent can tell this apart from siblings like search_datasheets or get_part_details without opening a 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', use section mode for named sections, search mode for targeted questions, prefer specific sections over 'all'. It also maps every datasheet_status value to a concrete next tool (check_extraction_status, prefetch_datasheets, request_datasheet_upload), which is textbook 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.

All SheetsData toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources