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

Annotations declare readOnly=false, destructive=false, idempotent=false, so the mutation safety profile is partly covered. The description adds an auth requirement ('Requires work_requests:write scope') and the ordering constraint on hierarchy resolution, which is real value beyond the annotations. It doesn't describe side effects, error behavior, or return values.

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 operation, then scope, then the flagged 'IMPORTANT' workflow. Every sentence is functional; the only mild waste is the partial duplication of the resolution steps already embedded in the schema.

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-param mutation tool with no output schema, the description covers the two things an agent most needs: the authorization scope and the non-obvious hierarchical ID resolution. Missing return/side-effect detail is acceptable given no output schema exists, though it could mention what a created request yields.

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 description coverage is 100%, and the description's hierarchy guidance largely duplicates what the schema descriptions already state ('resolve first via list_sites', etc.). It does reinforce that all three IDs should be supplied explicitly despite only title being required, which is a small addition, but the baseline of 3 applies when the schema carries the parameters.

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?

Starts with a specific verb+resource ('Create a new work request'), which is unambiguous against the many sibling create_* tools. It does not explicitly distinguish itself from the nearest lookalike (create_work_order), but the resource name is distinctive enough that an agent can tell them apart.

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 a required scope (work_requests:write) and a concrete imperative workflow for the hard part of the call: resolve the location hierarchy top-down via list_sites → list_buildings → list_locations. It states how to use the tool but offers no when-not or explicit alternative conditions.

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