Delimit Agent Dispatch

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

The description thoroughly discloses side effects: it writes a JSON record to disk, adds an audit log entry, coerces comma-separated strings to lists, and does NOT spawn a subagent. It even states that the caller is responsible for invoking the Agent tool separately and notes that this surface is not license-gated. The write behavior is consistent with readOnlyHint=false and destructiveHint=false, so there is no contradiction.

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 long, but every section earns its place: purpose, usage boundaries, sibling differentiation, and side effects are all critical for a tool that could easily be mistaken for an execution tool. Key information is front-loaded with clear headings and the most important caveat ('records dispatch but does NOT run the work') appears early.

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?

For a tool with 7 parameters, false read-only/destructive hints, and an important non-execution caveat, the description is complete. It covers the dispatch lifecycle, side effects, sibling alternatives, coercion behavior, and what the caller must do next. An output schema exists, so return-value documentation is not required.

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?

The schema already has 100% description coverage for all 7 parameters, so the baseline is 3. The tool description adds meaningful semantic value by explaining that tools_needed and constraints are coerced from comma strings to lists, and by framing the parameter set as the engineering-work surface with assignee, tools_needed, and constraints. This goes slightly beyond the schema descriptions.

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 concrete verb and resource: 'Record an engineering-task dispatch with full audit trail.' It explicitly distinguishes the tool from actual execution by stating it records intent rather than running the work, and it names sibling tools it is not (status, handoff, complete). An agent can immediately understand what this tool does and how it differs from nearby tools.

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 dedicated 'When to use' and 'When NOT to use' sections with specific conditions: use as the planning/audit surface when delegating parallelizable engineering work, and avoid for auto-execution, conversational tasks, sub-5-minute work, or missing functions. It also names alternative tools explicitly (delimit_agent_status, delimit_agent_handoff, delimit_agent_complete), leaving no ambiguity about selection.

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