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

Annotations already tell the agent this is a non-destructive, non-idempotent write. The description adds value beyond them by disclosing the required work_orders:write scope and a non-obvious server-side validation rule (an order without an asset/location association is rejected), which is real behavioral context an agent cannot infer from the schema.

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?

Front-loads the action, then layers REQUIRED, RECOMMENDED and resolution-order guidance in scannable labeled segments. Every sentence carries an actionable rule; nothing is filler despite the density of a 24-parameter tool.

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 24-parameter mutation with only coarse annotations, the description covers auth, hard validation rules, recommended categorization, and dependency resolution ordering. The remaining gap is what a successful call returns, which matters slightly more here because no output schema exists, though the return of a create tool is largely predictable.

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, but the description adds meaning the schema lacks: it declares site_id/building_id and an association as REQUIRED even though the schema only marks title required, and flags work_category_id as RECOMMENDED rather than optional. It does not address the id-vs-ids pairing or assignees/assigned_to alternatives beyond what the schema already documents.

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 work order') plus the fields the server actually requires, so the agent knows exactly which entity is being created. It never names a sibling, so the agent gets no explicit help distinguishing this from create_work_request or create_work_order_schedule in a 250+ tool list.

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?

Gives explicit preconditions and sequencing: resolve the location hierarchy top-down (list_sites -> list_buildings -> list_locations), look up work_category_id via list_work_categories, and ask the user which association applies when neither asset nor location is present. This is exactly the when/when-not/precondition guidance the dimension asks for.

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