delegate

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

With no annotations, the description fully discloses key behaviors: reads/edits files, runs shell commands confined to working_dir, returns a summary plus git change report, and is safe for concurrent invocation with in-flight runs bounded by LOCAL_VIBES_MAX_CONCURRENCY. This goes well beyond minimal expectations.

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?

About five sentences, each carrying distinct value: purpose, use cases, sandbox behavior, task composition advice, and concurrency notes. It is front-loaded with the main action and uses a dash-separated list for examples. Slightly longer than minimal, but all content is pertinent.

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?

Covers purpose, usage, behavioral constraints, output format, and concurrency. No output schema exists, but the description mentions the return format (summary plus git change report). It lacks explicit failure-mode or error-handling details, but given the tool complexity and lack of annotations/siblings, it is substantially complete.

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 100%, so each parameter already has a description. The tool description adds extra context by clarifying that the task must be self-contained, working_dir is the sandbox root, and read_only disables writes/edits/bash. This enriches the schema without redundancy.

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?

The description opens with a specific verb and resource: 'Delegate a self-contained coding or research task to a LOCAL model running in its own sandboxed agent loop.' It clearly defines what the tool does and distinguishes it from inline execution. Even without sibling tools, the purpose is unmistakable.

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?

Explicit guidance is given with 'USE PROACTIVELY to offload grunt work' followed by concrete examples (codebase searches, boilerplate, mechanical multi-file edits, test scaffolding). It also advises giving 'ONE clear, self-contained task with enough context to act without follow-up questions' and notes concurrent safety and a concurrency bound.

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