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

Annotations already indicate a write (readOnlyHint false), idempotent (idempotentHint true), and non-destructive (destructiveHint false). The description goes further: it explains the default assignment to the caller, the notification behaviour, the requirement and purpose of idempotencyKey to avoid duplicates, and the security warning about CRM field values. This adds substantial behavioural context beyond the annotations, with no contradiction.

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 two paragraphs that pack assignment logic, idempotency, security, and linking constraints. Every sentence adds value; no filler. It is front-loaded with the core action. Slightly dense but appropriate for the complexity, and the structure is logical.

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?

With 8 parameters, a nested object, low schema coverage, and no output schema, the description covers the non-obvious behaviours: default assignment, notification, idempotency, security. It does not explain the format of dueAt or the priority enum, but those are in the schema. It also doesn't mention what happens after creation (e.g., ID of new task), but that's not necessary given the tool outputs nothing per the schema absence. Overall, it is complete for safe and correct 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 schema covers only workspaceId with a description (13% coverage). The description compensates by explaining assigneeId (source from list_record_owners, never invent, assign only on instruction) and idempotencyKey (required, fresh unique key). It also notes that linkedRecord must be one the caller may view. It does not add meaning to dueAt, priority, or description, but the critical parameters are addressed.

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 opens with a clear verb+resource: 'Creates a task', and adds the optional link to a record and the assignment behaviour. It distinguishes from siblings like create_activity and create_record by referencing task-specific semantics (assignment, notification, idempotency). The purpose is unambiguous and specific.

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 gives detailed guidance on assigneeId sourcing (from list_record_owners) and when assignment is appropriate, and mandates a fresh idempotencyKey per intended task. However, it does not contrast this tool with alternatives like create_activity or create_record, so an agent may not know when to pick this over a sibling. The guidance is about parameter usage rather than tool selection.

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