update_work_package

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

Far beyond what the annotations convey: the description discloses that the patch is validated first, that omitted fields stay unchanged, that 'none' is a sentinel for clearing, that version/target_versions are mutually exclusive, that certain changes are refused when the package holds an assignment in a project not covered by OPENPROJECT_READ_PROJECTS, and that a closing status auto-fills percentage_done/remaining_time with a hard-error edge case. This is exactly the context an agent needs to avoid a failed or destructive call.

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?

After a one-line purpose statement the text becomes an undifferentiated block of field notes with no headings or grouping, and the percentage_done/closed-status caveat is spread over four sentences that restate the same derive-versus-explicit rule. Each fact is useful, but the lack of structure and the repetition cost the reader.

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 22-parameter mutation tool with no output schema, no enum hints and heavy instance-dependent behavior, the description covers the dangerous and non-obvious parts well. It falls short on describing what the call returns (preview payload vs. applied result) and leaves custom_fields entirely unexplained.

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 9% schema description coverage across 22 parameters, the description carries almost the entire burden and largely does: assignee, parent, version, target_versions, sprint, estimated_time, remaining_time, duration, percentage_done and the 'none' unassign sentinel for assignee/responsible/category/project_phase are all explained with formats and examples. Gaps remain for custom_fields, type, priority and start_date, which are undocumented in both schema and description.

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 opening sentence names a specific verb and resource ('Update a work package'), so the operation is unambiguous. It does not, however, distinguish itself from the sibling bulk_update_work_packages or explain the boundary with create_work_package, which it only references as a documentation surrogate.

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?

Usage context is implied by the field-by-field semantics rather than stated, and there is a helpful prerequisite ('Call list_users to find ids') plus a pointer to create_work_package for the confirm/preview contract. But nothing tells the agent when to prefer this over bulk_update_work_packages, and no explicit when-not guidance is given.

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