Update Task

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

Annotations already supply idempotentHint=true. The description reinforces idempotency with concrete explanation ('re-sending same values is a no-op') and adds specific behavior on null sprint_id. No contradictions. Adds value beyond annotations.

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, each serving a distinct purpose: purpose+idempotency, specific null behavior, and ID resolution guidance. Front-loaded with the core action. No redundant or verbose phrases.

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 purpose, idempotency, partial update, null handling, and ID resolution. No output schema exists, so return value explanation is not required. Lacks error handling or permission details, but given parameter complexity and annotations, it's sufficiently complete for an agent.

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 coverage is 100%, so baseline is 3. Description adds value by explaining the null removal behavior for sprint_id and the partial update semantics ('fields omitted stay unchanged'). Provides extra guidance beyond raw schema.

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 the verb 'update' and resource 'task', specifies partial update semantics ('fields you omit are left unchanged'). Distinguishes from siblings like create_task, delete_task, and other update tools by focusing on task-specific fields.

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 instructs to resolve IDs via get_task/list_tasks and pm_meta/list_* reads, and never guess them. Clearly states only 'id' is required. While it doesn't contrast with alternatives, the guidance is actionable and reduces guesswork.

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