Skip to main content
Glama
CHRONOS-AGENT

CHRONOS-AGENT

chronos_refactor_symbol

Performs graph-edge-verified multi-file symbol refactoring—preview usages, rename, or safe-delete—while separating verified edits from ambiguous sites and enforcing syntax validation with rollback.

Instructions

Perform graph-edge-verified multi-file refactoring (preview_usages, rename, safe_delete). Separates verified CALLS/TESTS/import edits from ambiguous member-access/shadowed candidate sites, enforces multi-file syntax validation + atomic rollback, and guards public/entrypoint/trait-impl deletions.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "symbol": "<symbol>",
      "action": "<action>"
    },
    "name": "chronos_refactor_symbol"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNoOptional defining source file path for symbol disambiguation
forceNoOverride ambiguity/homonym or dependent guards when applying rename/safe_delete (default: false)
actionYesRefactoring action: preview_usages | rename | safe_deletepreview_usages
symbolYesTarget symbol name or 'Class/method' path to analyze, rename, or safely delete
dry_runNoPreview multi-file diff and candidate sites without writing disk (default: false)
new_nameNoNew identifier name (required when action == 'rename')
max_answer_charsNoOptional maximum character budget for the response (default: 24000; <= 0 disables truncation)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
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 substantial work: it discloses that edits are graph-edge verified, that ambiguous member-access/shadowed sites are separated out as candidates rather than blindly changed, that multi-file syntax validation and atomic rollback are enforced, and that public/entrypoint/trait-impl deletions are guarded. It still omits what happens when validation fails, whether guards reject or merely warn (the force param hints at rejection), and any output/permission context.

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?

A single front-loaded sentence that packs the action list first and the safety guarantees after, with no filler. It is dense with project-specific jargon (CALLS/TESTS, shadowed candidate sites) but that vocabulary is load-bearing rather than padding.

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

Completeness3/5

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

For a 7-parameter mutating refactoring tool with no annotations and no output schema, the description covers safety behavior well but says nothing about what preview_usages actually returns (candidate site listing, diff shape) or how results are reported for rename/safe_delete. An agent would still need to probe the output format for the preview path.

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 all seven parameters are already documented in the schema, including force, dry_run, and new_name. The description adds conceptual framing (graph verification, ambiguity guards) that explains why force exists, but contributes no parameter-level syntax or format detail beyond the schema — baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'graph-edge-verified multi-file refactoring' — and enumerates the three supported actions (preview_usages, rename, safe_delete), so the agent knows exactly what operation family this covers. It does not name or contrast with the apparent sibling chronos_edit_symbol, so the boundary between 'refactor' and 'edit' is left to inference.

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

Usage Guidelines3/5

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

The action list implies which mode to pick for previewing versus mutating, and the mention of ambiguity/homonym guards hints that preview should precede destructive actions, but this is never stated. There are no explicit when-to-use/when-not rules and no named alternative among the many sibling tools (edit_symbol, blast_radius, mutation_gate).

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