review_draft

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is covered. The description adds the equivalence to review_ticket and the rationale for the pre-creation check, which is valuable behavioral context. It does not contradict annotations. The extra instruction to fix rather than report is an agent directive, not a tool trait, so it doesn't inflate the score further.

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 three short paragraphs, front-loaded with the core instruction. The first sentence is direct and actionable. The subsequent paragraphs justify the tool's existence, which is relevant for usage but slightly verbose. Every sentence earns its place, though the rationale could be tightened. Overall well-structured.

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?

The output schema exists, so return format is covered. The description explains the tool's purpose, when to call it, and its relationship to review_ticket. It does not mention edge cases or error handling, but for a read-only check tool this is adequate. The key context—why this tool exists and what it guarantees—is present.

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 must compensate by explaining parameter semantics. It does not. The parameter names (title, description, labels, project, tracker) are self-explanatory in context, but no format, constraints, or relationship is described. For a tool that validates a draft, the description gives no insight into what fields matter or how they are validated, leaving the agent to guess.

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 opens with a clear verb and resource: 'Check a ticket you have written but not created yet.' It explicitly ties the tool to review_ticket, stating it is the same measurement, which distinguishes it from sibling tools like review_ticket and review_open_tickets. No ambiguity remains about what the tool does.

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 gives explicit when-to-use guidance: 'Call this on your own draft before showing it to the user.' It explains why (point of no return, notifications, edit history) and implies when not to use it (after creation, use review_ticket). This is unambiguous routing to the correct workflow step.

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