Skip to main content
Glama
tenatarika

vex

by tenatarika
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

impact

Assess delete or rename safety for a symbol by combining reference, text, and call-graph checks into a safe/unsafe/uncertain verdict.

Instructions

Delete-safety blast-radius report. Composes four independent reference channels — strict refs (binder-resolved v5 edges), the legacy FST refs, grep \b<Name>\b against the project, and direct call-graph callers — into a single verdict (safe / unsafe / uncertain). Use this BEFORE proposing to delete or rename a symbol; one call collapses what CLAUDE.md previously documented as a manual dance across usages → grep → callers. Verdict rule: unsafe if strict_refs > 0 OR call_graph_callers > 0 (binder/graph confirmed real usage); uncertain if only text channels (FST / grep) hit (likely string-dispatch / decorator / comment mentions); safe only when every channel reports zero hits. results shape: { symbol, verdict, verdict_explanation, channels: { strict_refs, fst_refs, grep_word_boundary, call_graph_callers } } where each channel block has { available, count, sample[], truncated }.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoDEPRECATED — use `symbol`. Pre-v1.7 alias, still accepted; emits a deprecated_args notice in _meta.
depthNo(v1.21.0) BFS hop budget for transitive callers. `1` (default) reports direct callers only via `call_graph_callers`; `>= 2` enables the `transitive_callers` channel, walking the call graph backward up to N hops. Silently clamped to `[1, 16]`. Use to see the full upstream blast radius (`outer -> middle -> leaf` chain surfaces `outer` at depth=2).
symbolYesExact symbol name to assess — canonical key.
excludeNoBlacklist results by path glob; wins over include (repeatable).
includeNoWhitelist results by path glob, gitignore syntax (repeatable). Applied to every channel — useful for scoping to e.g. `src/**` when assessing a library symbol.
workspaceNoMulti-repo: fan out across every repo declared in the nearest `.vex-workspace.toml` (set `project_root` at or above it — the manifest is found by walking up). Results become an object `{workspace, repos:[...]}` grouped by repo, NOT the flat per-tool array — branch on shape. `why` is ignored in workspace mode (single-repo only).
auto_updateNoAuto-update the index if stale, or bootstrap it if missing, before running (default: true)
async_updateNoWith auto_update, refresh a stale index in the background instead of waiting for it: results come from the index already on disk and _meta.vex.dev/stale says so (default: false)
exclude_docsNo(v1.20.1, D4 parity) Opt-in: drop text-channel hits in prose-format files (`*.md`/`*.markdown`/`*.txt`/`*.rst`/`*.adoc`). Default off so a symbol mentioned only in CHANGELOG still yields `uncertain`; pass when you want a code-only blast radius (binder channels are unaffected).
project_rootNoAbsolute path to the project root (defaults to the MCP working directory)
exclude_testsNoDrop test files from the results (tests/ dirs, *_test.*, test_*.py, *.spec.ts, __tests__/, tests.rs, ...; same set as tests_for). Composes with include/exclude. Path-based only: Rust unit tests inside a `#[cfg(test)] mod tests` block of a non-test file are not excluded.
no_stale_checkNoSkip the staleness check that runs before each call; assumes the index is fresh. Redundant when `auto_update` is true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.27.3

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses the exact verdict rule (unsafe if strict_refs>0 OR callers>0, uncertain on text-only hits, safe only on all-zero) and the semantics of each channel. It is silent on read-only nature, auth/permissions, and rate limits, keeping it from a full 5.

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?

Front-loaded with the core purpose, then the verdict rule, then the results shape — a logical progression. It is dense and slightly long with heavy parenthetical/backtick notation, but nearly every clause carries information an agent needs.

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

Completeness5/5

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

There is no output schema, so the description compensates by spelling out the return shape { symbol, verdict, verdict_explanation, channels{...} } and each channel block's fields. Combined with the fully-covered input schema, an agent has everything required to call and interpret it.

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?

Schema description coverage is 100%, so the schema already documents all 12 parameters; baseline is 3. The description references concepts (transitive_callers channel, prose-file text hits) that map to params like `depth` and `exclude_docs`, but adds no syntax or format detail beyond the schema.

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+resource ("Delete-safety blast-radius report") and precisely scopes it as composing four named reference channels into a single verdict. An agent can distinguish it from siblings like `usages`, `grep`, and `callers` because the description explicitly names those as the channels it subsumes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use this BEFORE proposing to delete or rename a symbol" gives an explicit trigger, and it routes the agent away from the manual usages → grep → callers dance. This is a clear when-to-use with the alternatives named.

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

Deploy Server

Other Tools