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

Annotations already declare idempotentHint=true, destructiveHint=false and closed-world scope, so the burden is lighter. The description adds real behavioral context beyond them: the call is confined to one project (no cross-project side effects) and returns the project identity alongside the result, which the annotation set does not convey.

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 scope constraint front-loaded ahead of the functional statement, so nothing is wasted. The second sentence stacks scope, action, and id format slightly densely, but it remains readable.

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 2-parameter, closed-world removal tool with no output schema, the description covers scope, id sourcing, and id format, so an agent can invoke it correctly. The only small gap is that the returned payload beyond 'project identity' is only gestured at, which is acceptable given there is no output schema.

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 50%, so the description must carry weight, and it does: it documents the ids value format (array or comma-joined 'rg1,rg2') that the schema leaves completely blank, adding genuine meaning. The project_id sourcing rule in the description also reinforces the schema's own description of that parameter.

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 gives a specific verb+resource ('Remove region effects by id') and an evaluator can immediately infer it is the inverse of the sibling add_region_effect. However, it never names a sibling explicitly, so the differentiation is left to inference rather than stated.

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 provides clear operating context: the call is PROJECT-SCOPED, acts only on the explicit project_id, and the active-project pointer must never be used to guess scope, pointing at list_projects/open_project/project_state for the id. It stops short of stating when-not-to-use it or naming alternative removal tools.

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