plan

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

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds behavioral details: 'no edit until accepted' for architect, outputs a plan with specific components. This extends beyond annotations without contradiction, though some behaviors like idempotency are implied but not explicit.

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 dense and packs significant information into a single sentence structure. It is front-loaded with the core purpose. Some clauses are dense and could be clearer, but overall efficient with no wasted words. A slightly more structured format could improve readability.

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?

Given no output schema, the description outlines the plan's expected contents (reuse candidates, blast radius, decision_points, steps, verify commands). It covers roles and suggests pairings. For a planning tool, this provides sufficient context for an agent to understand what the tool produces and when to use it.

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 covers all 4 parameters with descriptions (100% coverage). The description adds context for the 'role' parameter, explaining the architect role's behavior (design Q&A, cite symbols, no edit). For other parameters, schema descriptions suffice, so description provides marginal additional value.

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 clearly states the tool's purpose: 'turn a task into a grounded plan BEFORE writing code'. It specifies key elements (reuse candidates, blast radius, decision_points, steps) and distinguishes roles like architect vs others. Also suggests preferring 'kickoff' for similar tasks, differentiating from siblings.

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?

Provides explicit when-to-use guidance: before writing code. Describes role-specific usage: architect for design Q&A with no edits until accepted, other roles for security/performance/refactor/feature. Recommends alternative tool 'kickoff' for the same pack with orient/docs, giving clear context for choosing this tool.

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