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

With no annotations provided, the description carries the behavioral burden. It discloses that this tool creates and links back to a handoff, and it surfaces a meaningful prerequisite for open questions (epic linkage). However, it does not disclose what happens if both `handoffId` and `key` are provided, how errors are surfaced, or what the created object looks like in response.

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?

Three sentences, all information-dense and front-loaded. The core action comes first, followed by the most important conditional constraintchers, then the input-parameter rule. No filler or repetition.

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?

For a create-style tool with no annotations, no output schema, and 5 parameters, the description provides the central usage and constraint but leaves gaps: no mention of return value, error behavior, or what happens to the handoff after derivation. It is usable but not fully self-sufficient.

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 only 20%, so the description must compensate. It does so by explaining the key parameter relationship ('Provide either `handoffId` or `key`') and by tying the `type` parameter to the two creation modes. It does not explain `title` and `description`, though those are reasonably inferable from the schema and the creation 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 uses a specific verb ('Create') and resource ('a task or open question from a handoff'), immediately distinguishing this from sibling tools like create_task and create_open_question by adding the handoff context and the 'linked back' behavior. It clearly states the two possible result types.

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 conveys when to use this tool: when you have a handoff (identified by `handoffId` or `key`) and want to derive a linked task or open question. It also gives an important conditional guideline: open questions require the handoff/task to be linked to an epic, while tasks do not. It does not explicitly name sibling alternatives or say 'use create_task for non-handoff tasks,' but the context is clear enough.

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