Retry network security policy

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

Beyond the annotations, it discloses that the pending policy may replace firewall rules and remove network access, the exact permission scopes required (networking:read vs networking:manage, and that full/read defaults do not grant networking), backend enforcement of ownership/feature/2FA, and the full polling contract (in_progress, reason_code/reason_kind, next_check_seconds). It also explains transport-uncertainty recovery with the original idempotency key, which is rich context the annotations alone cannot 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?

The purpose is front-loaded in the first sentence, followed by the destructive warning, then permissions and polling semantics in a logical order. It is dense and long for a retry operation, but nearly every sentence carries operational information rather than filler.

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?

There is no output schema, so the description carries the return-semantics burden and does so well: an accepted operation is pending, not proof of connectivity, and the agent is told how to poll in_progress/reason_code and how to recover from transport uncertainty. For a destructive, open-world mutation with three parameters, nothing essential 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 already 100%, so the baseline is 3, but the description adds real meaning: it clarifies that policies[].network_id is the affected network to poll and that the idempotencyKey must be preserved with the unchanged body on uncertain recovery. It does not add format detail beyond the schema for project_id, but the added idempotency semantics push it above baseline.

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 states a specific verb and resource ('Retry the failed network security policy using its current desired state') and distinguishes the action from the read path by pointing to get_network_security_policy for polling. It does not explicitly contrast with the closest sibling, retire_network_security_policy, so sibling differentiation is partial rather than complete.

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 clear preconditions: inspect the desired state first, read current capabilities and owned resource state, obtain approval for the exact change, and poll the correct sibling (get_network_security_policy) rather than generic operation IDs. It does not name when this should be preferred over retire_network_security_policy or other remediation paths, so it stops short of full when/when-not coverage.

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