task_update

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

Without annotations, the description carries the full burden. It successfully discloses the non-mutating workflow behavior (stays in same activity state) but omits safety details (permissions, idempotency), side effects (variable updates, history entries), or return value structure.

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?

Two high-density sentences with zero redundancy. First sentence establishes scope via colon-delimited list; second sentence provides critical behavioral guardrail. Every word earns its place.

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?

Adequate for basic operation given the empty schema and lack of annotations, but gaps remain: no positioning vs field-specific sibling tools, no output contract description, and the described metadata fields have no corresponding schema definitions.

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?

Input schema contains zero parameters (empty properties object), triggering baseline score of 4. The description adds semantic value by listing the six implicit updatable fields, compensating somewhat for the empty schema, though it cannot provide type/format details.

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?

Excellent specificity: verb 'Update', resource 'metadata of a user task', and explicit enumeration of six editable fields (name, description, assignee, due date, priority, parent task). The clause 'Does not advance the task in the workflow' sharply distinguishes it from the sibling task_complete tool.

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?

Provides only negative guidance ('Does not advance'), indicating when NOT to use it vs task_complete. Critically fails to guide selection between this general-purpose updater and sibling-specific tools like task_setAssignee or task_delegate that also modify assignees.

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