delete_worklog

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

Discloses destructive nature, mandatory dryRun step, adjustEstimate=auto behavior, and permission constraints. No annotations provided, so description fully carries transparency burden.

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?

Dense but clear paragraph; front-loaded with warnings and procedure. Could be slightly more structured (e.g., bullet points), but no wasted words.

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?

Covers procedure, permissions, parameter sources, and effect on estimate. Lacks explanation of return value/response format, but this is a destructive action where typical output is minimal.

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 covers all 3 parameters. Description adds context: dryRun for preview vs. actual delete, worklogIds sourced from list_worklogs, and adjustEstimate behavior. Exceeds baseline 3.

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?

Clearly states 'Xoá 1 hoặc nhiều worklog trên 1 Jira issue' (delete one or more worklogs on a Jira issue). Distinguishes from sibling tools like log_work and list_worklogs.

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?

Explicitly mandates dryRun=true first, user confirmation, then dryRun=false. Also notes permission restriction (only own worklogs or admin) and suggests using list_worklogs to obtain IDs.

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