Retry private network port

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

Goes well beyond the annotations with decisive behavior: a detach retry can remove private connectivity, required auth scopes (networking:read vs networking:manage, and that full/read defaults do NOT grant networking), backend-enforced ownership/feature/2FA locks, and the crucial 'accepted != connectivity' caveat. It also explains the in_progress/reason_kind/reason_code polling protocol and prohibits automatic retry — far richer than the destructive/idempotent hints alone.

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?

It front-loads the core action and the riskiest fact (detach retry removes connectivity) early, which is good. However, it is a very dense, multi-clause paragraph heavily loaded with jargon (reason_kind waiting, next_check_seconds, in_progress) that reads as a concatenated spec rather than cleanly separated guidance.

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?

Given a 5-parameter, destructive, open-world async operation with no output schema, the description covers the critical unknowns: safety, auth, idempotency, and result-polling semantics. It is nearly self-sufficient; only the return payload shape and any rate/pagination limits are left unaddressed.

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 80%, so the schema already documents most parameters. The description adds meaning by tying the action to 'the PORT generation' and by warning that 'restart' is only for an approved restart and the idempotency key must be preserved unchanged. expected_generation remains undocumented in both places, so no extra credit beyond the 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?

States a specific verb+resource (retry the failed current port operation) and the generation/approval mechanics involved. It distinguishes itself from attach_* by naming the 'failed current operation' scope, but it never explicitly names its closest siblings like retry_private_network, so the reader must infer the boundary.

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 clear conditions: 'Inspect the failed operation first', 'Read current capabilities and owned resource state first; obtain approval for the exact change', and 'reuse only the original key and unchanged request' on transport uncertainty. It stops short of naming an alternative tool or spelling out when not to retry at all (e.g. abandon instead of retry).

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