create_subtask

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

Annotations already declare a destructive, non-idempotent, open-world write, so the bar is lower; the description still adds real behavior beyond them — payload validation before writing, the non-deterministic ID ordering under concurrency, and the mutually exclusive version fields. It omits the preview/confirm workflow (only documented in the confirm parameter) and says nothing about permissions or what a validation failure looks like.

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?

Purpose is front-loaded in the first sentence and each following sentence adds a distinct constraint (validation, ordering, version exclusivity) with no filler. The mid-sentence line breaks make it slightly harder to scan, but nothing is redundant.

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 15-parameter mutation with no output schema, the description covers the tricky interactions but leaves the agent without guidance on the preview-then-confirm flow at the top level, on which of the many optional fields are typically required, or on failure behavior. Adequate but clearly incomplete for this schema size.

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?

With 15 parameters and only 13% schema description coverage, the description must compensate and largely does not. It explains target_versions (multi-version assignment) and its exclusivity with version, but the other thirteen parameters — type, subject, assignee, category, priority, dates, responsible, custom_fields, project_phase, confirm — get no semantics at all.

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?

States a specific verb and resource ('Create a subtask') and pins it to a required parent ('under an existing work package'), which distinguishes it from the generic create_work_package sibling. It does not explicitly say 'use create_work_package for top-level items', so the sibling boundary is implied by the parent requirement rather than spelled out.

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?

Gives concrete routing guidance: use bulk_create_work_packages when ordering across several new items matters, and target_versions vs version cannot be combined. It does not state prerequisites such as required permissions or when a subtask should be created versus a child work package via create_work_package.

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