Search and browse projects by language and name. Use this first to discover projects, then use other tools with the repo name.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number (1-based, default 1) | |
| repo | No | Filter by repository name | |
| query | No | Search by project name (case-insensitive contains) | |
| language | No | Filter by language (e.g., Python, TypeScript, CSharp) | |
| page_size | No | Results per page (default 20, max 100) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only says 'Search and browse projects' without detailing pagination, read-only nature, result format, or how filters interact. The schema covers parameter details, but the description adds no behavioral context beyond a high-level verb.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the tool's purpose, followed by a clear usage directive. No wasted words; every part contributes to understanding the tool's role.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description should indicate what the tool returns (e.g., a list of projects). It doesn't. It provides good workflow guidance for discovering projects, but the lack of return-type and pagination details leaves a gap for an unannotated tool. Given the tool's simplicity, this is a minimal but adequate score.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description's phrase 'by language and name' highlights the key filters (language, query/repo) but does not add new parameter-level details beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search and browse projects by language and name' with a specific verb and resource. It distinguishes the tool as the entry point for discovery ('Use this first to discover projects'), setting it apart from sibling tools that operate on specific repos.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives explicit when-to-use guidance: 'Use this first to discover projects, then use other tools with the repo name.' This provides a clear usage sequence, but it does not name specific alternative tools or explicitly state when not to use it, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct purpose: callers vs callees vs usages vs tests_for are directionally different, grep vs search separates text from symbol queries, and outline/view/source/info each serve unique functions. No two tools clearly overlap.
All tools follow a uniform 'xmp4_<snake_case_noun>' pattern with no mixed conventions or camelCase. The names are terse, descriptive, and predictably formatted.
At 16 tools, this is slightly above the typical well-scoped range (3–15), but the breadth is justified by the comprehensive code-knowledge domain. Every tool covers a distinct feature, so the count feels reasonable rather than bloated.
The surface is remarkably complete for semantic code analysis: project discovery (xmp4_projects), symbol lookup (xmp4_search, xmp4_symbol_at, xmp4_info), navigation (xmp4_outline, xmp4_view, xmp4_source), relationship exploration (callers, callees, hierarchy, usages, tests_for), and supporting meta tools (guide, server, deps, grep). No obvious gaps exist for its stated purpose.
