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

Annotations only declare non-read-only, non-idempotent, non-destructive. The description goes well beyond that: it discloses that setting staging_cluster_id auto-provisions a preview DNS zone and installs external-dns, that dns_root_domain changes are refused while zones or records still exist under the old root, and that clearing fields via empty string disables previews/workspaces. This is exactly the side-effect context the annotations cannot carry.

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?

One dense paragraph that is front-loaded with purpose and the admin restriction before drilling into field semantics, so the most important facts come first. Some content, notably the demo_base_domain sentence, overlaps with the schema descriptions, which slightly reduces efficiency.

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 an 8-parameter mutation tool with nested objects, no output schema, and no required fields, the description covers authorization, partial-update semantics, clearing behavior, provisioning side effects, and the return value ('Returns the saved settings'). Nothing essential for correct invocation is missing.

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 cross-parameter meaning the schema does not: staging_cluster_id being the switch that enables previews and the interaction of demo_base_domain/demo_ingress_class_name/demo_tls_secret_name as an override of the platform zone. It explains relationships rather than restating individual field definitions.

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 scoped resource ('Update the organisation's AI environment settings'), and the organisational scope implicitly separates it from application-level siblings such as update_application_ai_config. An agent can identify what it mutates 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?

Explicitly gates usage with 'Organisation admins only' and explains the partial-update contract ('only the fields present in the call change') plus the empty-string clearing convention. It stops short of naming the read counterpart (get_ai_environment) or stating when not to use this tool.

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