create_task

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

Annotations indicate a non-readonly, non-destructive mutation, but the description adds key behaviors: the connector rejects multi-target inputs, repeat.on is derived from dueOn when omitted, and ownerId cannot be cleared once set. These go beyond the annotation hints.

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 paragraphs, each with a distinct purpose: core action, exclusion rule, and standalone usage. The most critical constraint (mutual exclusion) is prominent. No wasted words.

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 9-parameter tool with a nested repeat object and no output schema, the description covers linking constraints, repeat derivation, owner behavior, and the connector's validation. It lacks return-value details, but that's typical without an output schema and not critical for invocation.

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?

The description clarifies the mutual exclusivity of partyId/opportunityId/projectId, explains the standalone-task behavior when all are omitted, and adds detail about repeat.on and ownerId limitations, enriching the schema's parameter descriptions (coverage 78%).

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?

States a specific verb and resource, 'Create a new task', and mentions optional links to party, opportunity, or project. Clearly distinguishes from sibling tools like update_task or complete_task by the creation action.

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 states the mutual-exclusion rule (pass at most ONE of the three IDs) and notes that omitting all is valid, creating a standalone task. It also mentions the rejection before HTTP call. While it doesn't directly compare with alternatives like update_task, the guidance is concrete and scenario-specific.

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