create_work_item

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

Annotations already flag a non-idempotent, non-destructive write tool, and the description goes well beyond that: it discloses permission pre-authorization (create/add/status), the partial-failure contract, and the specific error content (created Issue URL). This is exactly the kind of beyond-annotation behavior an agent needs to handle failures.

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?

Two dense sentences that front-load the core action and then the policy/failure details; every clause adds real information. It is slightly heavy but not padded.

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?

Behavioral context is strong (permissions, partial failure, verification), and no output schema exists so return-format detail is optional. But with 0% schema coverage on 5 parameters, a caller still lacks enough to fill in number/repository/title/body correctly, so the definition is incomplete for invocation.

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?

Schema description coverage is 0%, so the description carries the full burden for 5 parameters, yet it only indirectly touches 'owner' ('same authorized Project owner'). Nothing clarifies what number, repository, title, or body mean or the constraints on them, leaving four required params effectively undocumented.

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+resource (create a new GitHub Issue), ties it to the authorized Project, and clarifies the full flow (capture into Project + verify Backlog Status). This distinguishes it from the sibling add_github_project_item, which attaches an existing item rather than creating a new Issue.

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 supplies one real usage constraint – 'Admin/PM only in the current policy' – which tells the agent who should call it. However, it never explicitly states when to prefer this over add_github_project_item or other creation paths; the distinction is only implied by 'Create a new GitHub Issue'.

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