Skip to main content
Glama

iar_documentation_search

Read-only

Search the IAR user documentation (docs.iar.com): IAR Embedded Workbench for Arm, RISC-V, RH850, RL78 and RX (IDE, C/C++ compiler, assembler, linker, C-SPY debugger, C-STAT), IAR debug probes and cloud licensing. Set product to ewarm, ewriscv, ewrh850, ewrl78, ewrx, probes or lmsc. Returns page filenames and excerpts.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "iar_documentation_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoSearch query (e.g., 'ILINK config file', '#pragma location', 'C-SPY breakpoints'). Optional if 'keywords' is provided.
filterNoOptional: document type filter. Leave unset (default 'all') for IAR documentation.
intentNoOptional: Prioritizes (not filters) results by type. One of 'api', 'tutorial', 'guide', 'concept', 'example', 'migration'. 'api'=class reference, 'tutorial'=how-to guides, 'guide'=overviews, 'concept'=explanations, 'example'=code samples, 'migration'=porting guides.
moduleNoOptional: limit the search to one manual (e.g., 'iarccdevelopment', 'cspydebugging', 'cstatstaticanalysis', 'iarassembler', 'ideprojectmanagementandbuilding', 'migrationinformation').
productNoOptional: one of 'ewarm' (Arm), 'ewriscv' (RISC-V), 'ewrh850' (RH850), 'ewrl78' (RL78), 'ewrx' (RX), 'probes' (debug probes), 'lmsc' (cloud licensing). Compiler options and pragmas differ per architecture, so always set it.
versionNoOptional: product version to search (e.g., '10.10' for ewarm). Defaults to the latest available version.
keywordsNoOptional: array of keywords to search for. Results match ANY keyword. Example: ["pragma", "location", "absolute"]. Alternative to 'query' for multi-term matching.
max_resultsNoOptional: Maximum number of results to return (1-10). Default is 3.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

readOnlyHint=true already establishes this as a safe read, so the description's job is to add operational context beyond that. It does so with the only return-shape statement available ("Returns page filenames and excerpts") in the absence of an output schema, and with the directive to always set product because compiler options and pragmas differ per architecture. It does not cover result ranking, empty-result behavior, or whether pages are fetched live versus cached.

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 lead sentence front-loads the purpose and corpus, and the return statement is placed last where it is easy to find, with zero filler prose. The middle enumeration of product codes duplicates the schema's product description, so a small portion of the text does not earn its place.

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?

For an eight-parameter, fully documented, read-only search tool with no output schema, the definition covers purpose, corpus, the product selector, and the return shape — enough to call it correctly. The remaining gaps (empty-result behavior, follow-up via iar_documentation_read, and interaction between filter/intent/query/keywords) are modest rather than disqualifying.

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 coverage is 100%, so all eight parameters are already documented, including the product alias list and the query/keywords alternatives — the description's enumeration of the same aliases is largely redundant with the schema. The one increment it adds is emphasis that product should always be set, but it does not clarify interacting parameters such as intent-versus-filter or how query and keywords combine.

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 uses a specific verb plus resource ("Search the IAR user documentation (docs.iar.com)") and then scopes it across named product lines and toolchain components, which tells an agent exactly what corpus this covers. The closing sentence "Returns page filenames and excerpts" implicitly separates it from the sibling iar_documentation_read, which is the tool you would call on those filenames.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied rather than stated: an agent can infer it should search first and then read a returned page, and it is told to "Set product to ewarm..." when searching. However, there is no explicit when-to-use/when-not-to-use guidance, no statement about when to prefer this over iar_documentation_read, and no mention of what to do when a search returns nothing.

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