Extracts a target file’s code, one-hop outbound signatures, and inbound callers to map change impact within a 4,000-token context.
Extract the Surgical Context (< 4,000 tokens) for a target file: includes target code, 1-hop outbound signatures (bodies stripped), and 1-hop inbound callers.
| Name | Required | Description | Default |
|---|---|---|---|
| repo_path | No | ||
| target_file | Yes | Relative file path inside repository (e.g. 'services/order_service.py'). |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It usefully discloses scope and behavior: bodies are stripped and output is capped under 4,000 tokens, which tells the agent what it will and won't receive. It says nothing about read-only nature, side effects, permissions, or repo_path resolution, leaving real gaps for an unannotated 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?
One dense sentence with the return contents front-loaded and no filler. Minor deduction for the unexplained capitalized term 'Surgical Context', which reads as internal jargon rather than actionable phrasing.
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?
Since there is no output schema, the description correctly spends its words describing what comes back (target code, outbound signatures, inbound callers), which is genuinely useful. However, with no annotations and one of two parameters undocumented, an agent still lacks enough to invoke it confidently across repositories.
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 coverage is only 50%: target_file is documented in-schema, but repo_path is undocumented in both the schema and the description. The description mentions only the 'target file' and gives no indication of what repo_path means (default repo? absolute path?) or how it interacts with target_file. With half the parameters opaque, the description fails to compensate.
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 action (extract context) and enumerates the three components returned: target code, 1-hop outbound signatures with bodies stripped, and 1-hop inbound callers. The 'blast_radius' name is ambiguous, but the description resolves it. It does not differentiate from the near-duplicate sibling aisdlc_blast_radius or from localvibecode_build_graph, so it stops short of a 5.
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?
The token budget ('< 4,000 tokens') and 'surgical context' framing imply this is for cheap, targeted context gathering rather than full graph traversal, which hints at when to use it. There is no explicit when-to-use, when-not, or named alternative among the seven siblings, so usage must be inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.