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

Annotations only carry destructiveHint=true, so the description does real work: it discloses that each invocation produces a new record (non-idempotent, duplicate-prone) and that notification flags default to off unless explicitly set, which prevents silent no-ops. It stops short of stating permission requirements or what the response contains.

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?

Very compact and front-loaded: the write intent and endpoint lead, followed by the highest-risk conditional rules. The telegraphic phrasing ('INTERNAL_TASK needs requested_by_user') is efficient, though slightly terse for an unfamiliar caller.

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?

Given 16 parameters, no output schema, and thin annotations, the description covers the highest-risk unknowns: per-type required fields, notification defaults, and non-idempotency. It does not cover the three globally required fields or what identifier a successful create returns, which matters for chaining into doorloop_get_task.

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 75%, and the description compensates for part of the gap by spelling out the cross-field dependency that the schema itself does not encode (requested_by_user/tenant/owner, assigned_to_vendor per type). It also adds the default semantics for the notify flags. It leaves the type enum values and priority/status choices unexplained beyond the 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?

Opens with an explicit verb+resource ('WRITE: create a task in DoorLoop') plus the backing endpoint (POST /tasks), which cleanly separates it from the read siblings (doorloop_get_task, doorloop_list_tasks) and from doorloop_post_task_update. An agent can identify the operation without opening the schema.

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 supplies the key conditional rule for choosing which of the four type values to use and which companion field each demands, plus a warning that 'each call creates a new task' (duplication risk). However, it never explicitly contrasts with doorloop_post_task_update or states when an update should be preferred over a fresh create, so the alternative routing is only implied.

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