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

The annotations already mark the tool as read-only, idempotent, and non-destructive, and the description adds valuable behavioral context on top: the hierarchy is free-form, any task type may parent any other, and unusual shapes are team choices, not errors to correct. This prevents the agent from misinterpreting returned data and trying to 'fix' it. 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 core function is front-loaded in the first sentence, with usage guidance and caveats following in a logical order. It is longer than minimal, but every sentence earns its place: the free-hierarchy caveat and the create_task workflow note are both high-value, not filler.

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?

With no output schema, the description carries the burden of explaining what the tool returns, and it does: hierarchy, children, counts, progress, and optional deeper task levels. It also covers the important data-model caveat. It stops short of describing exact response shape or pagination, but for a read-only hierarchy tool the given context is strong.

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 the parameters are already documented. The description adds real semantic value by explaining exactly when include_tasks matters ('when you need the level below stories') and by clarifying the project_id role implicitly through the hierarchy context. It does not, however, address the schema's odd note that a required project_id can be 'omitted once'.

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 names a specific verb ('Returns') and a specific resource ('the project hierarchy'), and lists concrete contents: epics, children, counts, and progress. It also explicitly carves out its uniqueness ('the ONLY tool that reports per-epic numbers'), distinguishing it from sibling tools like list_tasks and get_task_stats.

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?

It gives explicit when-to-use guidance: 'Call it before create_task' to determine the proper parent, and tells the agent when to pass include_tasks=true. It also asserts exclusivity ('the ONLY tool that reports per-epic numbers'), which tells the agent not to look for this data elsewhere.

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