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

Despite annotations only saying the tool is not read-only and not destructive, the description details the meaningful side effect: it creates a 'decompose' task, imposes a dependency, and prevents claiming until real subtasks exist. This goes well beyond the annotation hints and supports correct expectations.

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?

Three short sentences, with the primary behavior in the first sentence and usage guidance at the end. No filler; the 'Break-down-as-work' label is slightly unusual but doesn't waste space.

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?

The description covers the core preconditions, side effects, and the blocking consequence, which is the main context an agent needs. It doesn't disclose return values or the assignee variants' precedence, but the schema supplies most mechanical details, so this is adequate without being exhaustive.

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 documents task_id, note, and assignee, while assignee_id and assignee_worker_id lack descriptions (60% coverage). The tool description adds context for task_id via the decompose-task flow but does not clarify how to choose between assignee, assignee_id, and assignee_worker_id.

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 action ('creates a `decompose` task') and names the exact resource it operates on. It also explains the effect on the target ('blocks the target... cannot be claimed') and gives the trigger ('under-specified task'), which clearly separates it from generic create_task/update_task/claim_task 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?

States an explicit condition: use when a task is under-specified, with concrete examples 'empty goal or definition_of_done.' It also says 'instead of guessing,' which discourages other paths, but it does not name specific sibling alternatives or exclusions.

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