Update network security group

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

Annotations already flag destructive, non-readOnly, idempotent, openWorld, but the description adds substantial context beyond them: full replacement semantics, that empty rules deny previously allowed traffic, that bound servers may be affected, backend enforcement of ownership/features/2FA, and that an accepted operation is pending rather than proof of connectivity.

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?

Purpose is front-loaded and every sentence carries operational content, but the later polling/idempotency passage is a dense run-on that would benefit from structure. It is information-rich rather than padded, so it stays above the adequate line without being maximally tidy.

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 complex destructive replace with six required params and no output schema, the description covers the full lifecycle: preconditions, auth, side effects on bound servers, asynchronous polling semantics, reason_code handling, and idempotent recovery on transport uncertainty. Nothing essential to 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?

With only 50% schema coverage, the description compensates by giving meaning to expected_revision ('at its expected revision') as a concurrency token and to idempotencyKey ('reuse only the original key and unchanged request'). It also frames name/rules as a complete replacement set, though it leaves group_id and project_id unaddressed.

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: 'Replace the complete group name and rule list at its expected revision.' The word 'Replace' and 'complete' distinguishes it from partial-update or clone siblings, and the revision framing signals optimistic concurrency. An agent can tell this apart from create/clone/delete security group tools 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?

Gives concrete when-to-use preconditions (read current capabilities and owned resource state first, obtain approval) and a follow-up action (poll get_network_security_policy per affected network and its policies[].network_id). It also states the auth requirement (networking:read for reads, networking:manage for changes) and that defaults do not grant networking.

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