create_work_package

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

Beyond the destructive/openWorld/non-idempotent annotations, it discloses non-obvious behaviors: validation is previewed before applying, built-in due-date shifting on non-working days with no opt-out, non-tool-error validation rejections that surface in `ready`/`validation_errors`, and server-completion-order ID assignment. These are exactly the behavioral traits an agent could not infer from annotations or schema.

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?

Front-loaded with purpose, then a dense sequence of parameter and behavior notes; nearly every sentence carries unique information (duration examples, due-date shift, concurrency ordering). Some sentences are long and wrapped awkwardly, but nothing is 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?

No output schema exists, and the description compensates by telling the agent to inspect `ready`, `validation_errors`, and `result.due_date` in the result. For a 19-parameter mutation tool this is close to complete, with the main residual gap being coverage of structural fields (type, project, custom_fields) whose id/name resolution rules are unstated.

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 only 11% schema description coverage across 19 parameters, the description carries most of the burden and does well for the trickiest ones: parent id vs display_id, assignee 'me'/numeric with list_users lookup, ISO8601 duration syntax with examples, and the target_versions/version mutual exclusivity with an explicit empty-list semantic. Unexplained remain project, type, subject, priority, responsible, category, custom_fields, project_phase, and the preview/confirm workflow (though the schema documents confirm).

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 first line names the verb and resource directly ('Create a work package'), and later sentences distinguish it from create_subtask and bulk_create_work_packages in the concurrency/id-ordering context. It does not explain when to prefer create_subtask (child creation) over this tool, so differentiation from siblings is partial rather than complete.

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 concrete routing advice: call list_users to resolve assignee ids, and use bulk_create_work_packages when relative ID creation order across a batch matters. There is still no explicit guidance on create_subtask vs this tool for nested creation beyond the parent-parameter note, and no prerequisites/permission guidance.

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