delegate_task

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

Beyond the readOnlyHint annotation, the description discloses that output is saved to a file whose path is returned, that think=true adds slower reasoning, that fast tier is ~1.4x quicker, and that the tool is unsuitable for correctness-critical tasks. No contradiction with annotations.

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?

The description is well-structured and front-loaded with the core purpose, followed by scannable Good-for and NOT-for lists. Every sentence adds operational value; no filler or repetition of schema fields.

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?

Despite having no output schema, the description explains the return value (file path) and covers context limits, performance trade-offs, and selection criteria. It is complete enough for an agent to decide when and how to call this tool correctly.

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?

With 0% schema description coverage, the description compensates by explaining context_files (absolute paths, ~90k chars), model_tier (fast vs strong speed), and think (reasoning/slower). However, timeout_s and max_tokens are not explicitly described, though 'ask for long outputs freely' indirectly hints at output limits.

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: 'Run a self-contained subtask on a LOCAL model and return its text.' This clearly distinguishes it from siblings like search_code and review_diff, and the Good-for list further scopes it.

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 description provides explicit 'Good for' and 'NOT for' sections naming concrete use cases (boilerplate, unit tests, docstrings) and exclusions (final correctness, full-repo reasoning). It also gives operational constraints like ~90k chars context and model_tier trade-offs.

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