create_work_item

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

The description discloses important behavioral constraints: the description field supports Markdown/rich text and requires formatType to be set accordingly; the URL returned from create_workitem_attachment is a temporary signed URL that expires in 30 seconds; and effort fields are system-controlled and cannot be modified via customFieldValues. These are non-obvious behaviors that the user needs to know.

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 description is well-structured with bullet points and is front-loaded with the primary purpose. It is slightly verbose due to the inclusion of detailed examples and warnings, but each sentence adds value and addresses important edge cases. The length is justified given the complexity of the tool.

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?

Given the tool has 15 parameters including a nested object and no output schema, the description covers the most contextually important aspects: the special handling of description, the prohibition on modifying effort fields, and the essential workflow for attachments. It does not explain every parameter, but it addresses the areas where users are most likely to make mistakes, making it sufficiently complete.

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?

While the input schema provides basic descriptions for each parameter, the tool description adds critical semantics: it clarifies how to handle the description and formatType parameters (including the caveat about Markdown), warns against putting effort fields in customFieldValues, and explains the role of the attachment-related steps. This goes beyond the schema to provide essential parameter usage context.

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 clearly states the tool's function as 'Create a work item', and provides additional context about handling description and effort fields. It distinguishes itself from sibling tools by directing users to alternative tools for specific sub-operations (e.g., attachment upload, effort records).

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?

The description provides explicit usage instructions: it explains the three-step process for inserting images (create attachment, get embedMarkdown/embedHtml, then update work item), and instructs users to use dedicated tools (create_effort_record, create_estimated_effort) for effort fields instead of customFieldValues. This effectively guides when to use this tool versus alternatives.

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