corbel

Overview Schema Source Related Servers Discussions Admin

impact

Trace the blast radius of a symbol change by walking the reverse call graph across multiple hops to find every caller that could be affected before refactoring.

Instructions

Trace the blast radius of changing a symbol: starting from the given symbol, walk the reverse call graph — direct callers, their callers, and so on across multiple hops — and return every symbol that could be affected by a change to it. Each affected symbol comes with a depth field (how many hops away it is) and a resolution field naming which index-wide lookup resolved that call edge (e.g. same-file, scoped, global-unique — scoped/global-unique both mean a single matching definition was found index-wide, see docs/mcp-tools.md), so results are grounded in real, resolved call relationships rather than a text search for the symbol's name (which cannot follow more than one hop and cannot tell a real call from a coincidental name match). Use this tool before refactoring — e.g. changing a function's signature or behavior — to find every place in the codebase that may need to change as a result, including indirect callers that a single-hop "find references" would miss. The response can be truncated to fit within a token budget and/or a hop-count depth; when either limit is hit, the corresponding flag is set (truncated/truncated_count for the budget, depth_truncated for depth) so a caller can tell which one cut the walk short. Results come from the local corbel index built by corbel index and only reflect the repository as of the last index run.

Input Schema

TableJSON Schema

Name	Required	Description
`file`	No	Optional file path to disambiguate when multiple symbols share this name.
`name`	Yes	The symbol name to start the impact analysis from.
`depth`	No	Optional cap on how many call-graph hops to walk outward (0 returns no affected symbols, 1 returns only direct callers, and so on). Defaults to corbel's internal maximum of 10 if omitted, which is also the hard ceiling — values above 10 are clamped to 10. Whichever of `depth` and `token_budget` is hit first stops the walk; `depth_truncated` in the response is true only if the depth ceiling (not the budget) is what stopped it.
`token_budget`	No	Optional cap on the size of the response, in estimated tokens. Defaults to corbel's built-in budget if omitted.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.0.0Sep 20, 2026

addedInput schema / properties / depth

Added value: +{
+  "description": "Optional cap on how many call-graph hops to walk outward (0 returns no affected symbols, 1 returns only direct callers, and so on). Defaults to corbel's internal maximum of 10 if omitted, which is also the hard ceiling — values above 10 are clamped to 10. Whichever of `depth` and `token_budget` is hit first stops the walk; `depth_truncated` in the response is true only if the depth ceiling (not the budget) is what stopped it.",
+  "type": "number"
+}

First observedv0.1.0Sep 6, 2026

TDQS

A4.3/5.0

Behavior5/5

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

With no annotations provided, the description carries the full burden and does so thoroughly: it discloses that results are grounded in resolved call relationships, that responses can be truncated with corresponding flags set, and that results come from the local corbel index and are only as fresh as the last index run. No contradiction with annotations exists because none are provided.

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 dense but not bloated, front-loading the core purpose before usage guidance, truncation flags, and index freshness. Some parenthetical detail could be tightened, but each sentence contributes decision-relevant information.

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?

Without an output schema, the description compensates by naming returned fields (`depth`, `resolution`), explaining truncation flags, and noting the index-freshness caveat. It stops short of giving a full response shape or an example, but it is enough for an agent to call the tool correctly.

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?

The input schema already documents all four parameters with rich descriptions, giving 100% schema description coverage, so the baseline is 3. The tool description adds context about truncation behavior and depth/token_budget interplay but does not need to re-explain parameter syntax.

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?

States a specific verb ('Trace') and a specific resource ('the blast radius of changing a symbol'), and explains the mechanism: walking the reverse call graph across multiple hops. It also contrasts itself with text-search/find-references behavior, which effectively distinguishes it from the sibling find tool even without naming it.

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?

Explicitly says 'Use this tool before refactoring — e.g. changing a function's signature or behavior' and explains that it catches indirect callers that a single-hop find-references would miss. It provides clear context but does not name the sibling tools directly or list when-not-to-use scenarios.

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

Deploy Server

impact

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools