find_indexed_referencesLocate identifier references via a SQLite workspace index and return matching snippets. Use it to see where a symbol appears across files without rescanning the project.
Find identifier references from the SQLite workspace index with snippets.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| limit | No | ||
| contextAfter | No | ||
| contextBefore | No | ||
| includePreview | No | ||
| refreshIfStale | No |
Changes observed during successful MCP inspections.
v1.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that results come from a SQLite index and include snippets, but says nothing about index staleness (even though a refreshIfStale parameter exists), pagination, or what happens when no index is built — significant gaps for a search 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?
A single tight sentence with no waste, front-loading the verb and resource. It is well-structured, though it is concise at the cost of the missing behavioral and parameter detail.
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?
For a 6-parameter tool with no annotations, no output schema, and zero parameter documentation, the description is far too thin. An agent cannot know how to bound results or control snippet context without opening the raw schema.
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 6 parameters. The description only implies the 'name' input and the presence of 'snippets', leaving limit, contextBefore, contextAfter, and refreshIfStale completely undocumented in both schema and description.
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?
States a specific verb (Find) and resource (identifier references), and adds the source ('SQLite workspace index') plus that results include snippets. This distinguishes it from the LSP-based siblings, but it never explicitly names find_references or lsp_references as the alternatives an agent should choose between.
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?
There is no when-to-use or when-not guidance. The phrase 'from the SQLite workspace index' hints that this is the indexed counterpart to the LSP tools, but nothing tells the agent when to prefer the index over live LSP references, nor mentions index prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.