Locate graph entities and source paths without loading the whole project, providing targeted context for AI agents to ground modifications in current project facts.
Search graph entities and source paths without loading the entire project.
| Name | Required | Description | Default |
|---|---|---|---|
| kinds | No | ||
| limit | No | ||
| query | Yes | ||
| locale | No | ||
| states | No | ||
| projectRoot | No | ||
| taskContextId | No | ||
| includeStructured | No |
Changes observed during successful MCP inspections.
v0.3.3Input schema / properties / taskContextIdAdded value: +{
+ "minLength": 1,
+ "type": "string"
+}v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. It does reveal one useful trait—does not load the entire project—which suggests a read-only, performance-conscious operation. However, it does not explicitly confirm read-only behavior, permissions, response formats, or possible error cases, leaving gaps for a no-annotation tool.
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?
The description is a single concise sentence that front-loads the core purpose and the key qualifier. Every word contributes value, with no repetition or filler.
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?
Despite a clear purpose, the tool has 8 parameters, no output schema, and no annotations. The description does not explain return values, parameter syntax, required setup like projectRoot/taskContextId, or how search results are structured. For a tool of this complexity, the description is far too skeletal to enable reliable invocation.
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 0% across 8 parameters, and the description provides no parameter-level meaning. Parameters like kinds, states, includeStructured, projectRoot, and taskContextId are left entirely unexplained, forcing an agent to guess their roles and formats.
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 states a specific verb ('Search') and resource ('graph entities and source paths'), and adds a distinguishing performance qualifier ('without loading the entire project'). This clearly separates it from mutation siblings like graph_mutate or graph_patch, even though those siblings are not named.
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?
No explicit guidance is given about when to use this tool versus alternatives. The phrase 'without loading the entire project' implies a lightweight search use case, but no alternative tools are mentioned and no exclusion criteria are provided. An agent must infer usage from the tool name and siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.