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

Annotations only declare destructiveHint=true, which the description is consistent with via 'Create' (POST /tasks), so there is no contradiction. The description adds the endpoint and required-field constraints, but says nothing about permission requirements for acting on another record, side effects, or whether the created task can be undone — meaningful gaps for a write tool whose annotation burden is only partially covered.

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 tight sentences with the required-field contract and the linking rule front-loaded, no filler, and the endpoint tacked on last. Nothing is wasted.

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 10-parameter mutation tool with no output schema, the description covers the required contract and one key parameter's source, but leaves the return value (e.g. the new task's jnid) and error/permission behavior unexplained. Adequate to invoke, not complete enough for an agent to handle the result confidently.

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 the baseline is 3, yet the description adds genuine meaning: it names the three required fields plus related_id, clarifies date_start is unix seconds and doubles as due time, and explains record_type_name comes from account settings (e.g. Task or Appointment), nudging the agent toward get_account_settings. It does not cover the other optional params, so it stops short of a 5.

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 specific verb and resource ('Create a task or appointment') and adds scope ('on a contact or job'), so the agent knows exactly what record is produced and what it attaches to. It is trivially distinguishable from sibling creators like create_contact or create_job.

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?

It states the operation and its required inputs, which implicitly tells the agent this is the tool for creating new tasks, but it never states when NOT to use it or points to alternatives such as update_task for modifying existing tasks or list_tasks for retrieval. Usage context is inferable rather than explicit.

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