reject_draft

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

Annotations already provide 'destructiveHint: true', indicating destructive behavior. The description adds that the tool does not create a memory and returns the rejected draft state. However, it lacks details on required permissions, side effects on related data, or the meaning of rejection in the broader context.

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 concise, with two sentences plus structured Args/Returns. However, the Args/Returns section could be trimmed or integrated into the main description to reduce redundancy. Still, it is well front-loaded with the key purpose.

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 two parameters, is destructive, and has an output schema, the description covers basic semantics but omits important context such as prerequisites for rejection, the relationship to memory drafts, and details about the output structure. The presence of an output schema does not compensate for the lack of description of what the returned JSON contains.

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 fills a critical gap. It explains that 'draft_id' is the identifier returned by 'draft_memory' and that 'reason' is optional for rejection. This adds meaningful context beyond the bare schema definitions.

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 'Reject a draft without creating a memory', specifying the verb 'reject' and the resource 'draft'. It distinguishes from sibling tools like 'merge_draft' or 'draft_memory' by implying that this tool only rejects without additional side effects.

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 no explicit guidance on when to use this tool versus alternatives. It only mentions that rejecting does not create a memory, which indirectly hints at a difference, but does not clarify scenarios where this should be preferred over other draft-related tools.

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