plan_tool_workflow

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds value by detailing that tool references are checked against the loaded catalog, never guessed, and unresolved references reported explicitly. No contradictions.

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 thorough but slightly long. However, it is well-structured with clear sections and bullet-like list for step spec fields. Could be more concise, but still effective.

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 the complexity of a planning tool with nested steps and dependencies, the description covers all aspects: input parameters, constraints (max 25 steps), resolution logic, return fields, and behavior. Output schema exists but description adds necessary context.

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 0%, but the description fully explains both parameters: steps (bounded max 25, each step dict with id, tool, hint, depends_on) and include_candidates (default false, returns up to 5 candidates). Also explains return fields in detail.

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 it builds a deterministic, read-only dependency/order plan across enabled backend tools. It uses specific verbs and resources, and distinguishes itself from siblings like invoke_tool and find_tool.

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?

Explicitly says 'Never executes any tool' and explains when to use (planning dependencies) and when not (execution). Provides alternative: find_tool for searching tools.

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