Clone network security group

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

Annotations only say non-readonly, idempotent, non-destructive and open-world; the description goes far beyond by disclosing scope requirements, backend ownership/feature/2FA-lock enforcement, that acceptance is pending rather than proof of connectivity, the polling contract (in_progress, next_check_seconds, reason_code/reason_kind), and the recovery rule of reusing the original idempotency key with an unchanged body and never auto-retrying. This is exactly the behavioral detail an agent needs for an async mutation.

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?

The purpose and the polling contract are front-loaded, and most sentences carry real information, but the description is a single dense paragraph with long run-on clauses and some redundancy ('Preserve reason_code' / 'never automatically retry'). It would be substantially more usable split into purpose, prerequisites, and result-handling sections.

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?

With no output schema and an async operation as the result, the description correctly covers how to interpret the returned operation/resource, what counts as failure, and how to recover from transport uncertainty. It does not say what the successful clone yields (e.g. the new group identifier) or whether rules and memberships are copied, which leaves a small gap for a 5-param required-argument mutation.

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 60%, so the description must carry part of the load, and it does: 'use the source group's current revision' explains expected_revision, 'into a new name' maps to name, and the idempotency guidance explains idempotencyKey's recovery semantics beyond the schema's terse note. project_id/group_id are already documented in the schema, so only the deeper semantics of the remaining params are added.

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 first clause states a specific verb and resource ('Clone an owned group into a new name') and adds the key constraint that the source's current revision is used. This is clearly distinguishable from siblings like create_network_security_group, update_network_security_group and delete_network_security_group without opening any 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?

It gives real preconditions: read capabilities and owned resource state first, obtain approval for the exact change, and it names the exact OAuth scopes required (networking:read vs networking:manage) while warning that full/read defaults do not cover networking. It stops short of naming an alternative tool for the non-clone case, so it is clear context without explicit routing.

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