Skip to main content
Glama

search

Use semantic similarity to query HoloViz and custom project documentation, returning relevant snippets or full documents.

Instructions

Search the HoloViz and any user defined project documentation using semantic similarity.

IMPORTANT: This is a general purpose search tool. Not just for searching the HoloViz documentation.

DO use this tool to search the HoloViz project documentation DO use this tool to search any additional user-defined project documentation. DO use the project_list tool to list the available projects.

BEST PRACTICES:

  • For initial exploration, use content=False to get an overview of available documents

  • Use content="chunk" for quick snippets, content="full" for complete documents

  • Adjust max_content_chars if you need more or less content per result

  • Set max_content_chars=None to get untruncated content (use with caution for large docs)

QUERY OPTIMIZATION: The search uses context-aware truncation that centers returned content on query keywords. To get the most relevant excerpts:

  • Use SPECIFIC terms: "CheckboxEditor SelectEditor" > "editor dropdown"

  • Use UNIQUE identifiers: "background_gradient text_gradient" > "styling colors"

  • Avoid COMMON terms that appear everywhere: "pandas", "import", "data", "widget"

  • Include CLASS/FUNCTION names: "add_filter RangeSlider" > "filtering with widgets"

  • Use MULTIPLE specific terms: Helps the algorithm find the right section

  • Target FEATURE-SPECIFIC vocabulary: Terms unique to the feature you're looking for

Example: Instead of "how to add pagination to a table", use "pagination page_size local remote" This ensures the truncated content focuses on the pagination section, not generic table info.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query using natural language or specific keywords. Natural language works for finding documents, but specific terms work better for content truncation. See QUERY OPTIMIZATION above. Good examples: "Button onClick on_click callback event", "hvPlot bar chart kind options" Okay examples: "how to style Material UI components", "interactive plotting with widgets"
projectNoOptional project filter. Defaults to None. Examples: "panel", "hvplot", "my-custom-project"
contentNoControls what content is returned. Defaults to "truncated". - "truncated": Full document content, smart-truncated around query keywords (default) - "chunk": Only the best-matching chunk from the document - "full": Full document content with no truncation (can be very large) - False: No content, metadata only (fastest) For backward compat, True maps to "truncated".truncated
max_resultsNoMaximum number of results to return. Defaults to 2. Increase if you need more options, but be mindful of response size.
max_content_charsNoMaximum characters of content per result. Defaults to 10000. Set to None for untruncated content (may cause token limit errors). Content is truncated at word boundaries with an ellipsis indicator.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

With no annotations provided, the description thoroughly discloses behavioral traits: semantic similarity search, context-aware truncation centered on query keywords, content options (truncated, chunk, full, false), and warning about token limit with max_content_chars=None. This provides comprehensive transparency.

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 description is well-structured with sections (IMPORTANT, BEST PRACTICES, QUERY OPTIMIZATION) and front-loaded with the main purpose. While verbose, each section provides essential guidance. A minor trim could improve conciseness, but the structure earns its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that an output schema exists (context signals indicate 'Has output schema: true'), the description does not need to fully explain return values. However, it does not mention that results are ranked by similarity or describe the output format. For a search tool, explaining that results contain document metadata and content is implicit from content parameter descriptions, but explicit mention would improve completeness.

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%, but the description adds significant value beyond schema definitions. It provides examples for query optimization, explains each parameter's behavior in detail (e.g., content options, max_content_chars truncation), and gives usage context. This extra information aids correct parameter invocation.

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 clearly states that the tool searches HoloViz and user-defined project documentation using semantic similarity. It distinguishes from sibling tools like *_get (specific documents) and *_list (listing projects) by emphasizing its general-purpose nature.

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?

The description provides explicit 'DO use' instructions for searching documentation and suggests using project_list to list available projects. It includes best practices and query optimization tips. However, it does not explicitly state when to use alternatives like *_get tools for retrieving specific documents.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MarcSkovMadsen/holoviz-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server