Skip to main content
Glama

Retry private network

retry_private_network
DestructiveIdempotent

Retry a failed private network operation, preserving its generation. Inspect the failure before retrying; use networking:manage for changes.

Instructions

Retry the failed current network operation only; preserve its current generation. It may resume a failed deletion or settings change, so inspect the failed operation before retrying. Requires explicit networking:read for reads or networking:manage for changes; full/read defaults do not grant networking. The backend enforces ownership, feature availability and service 2FA locks. Read current capabilities and owned resource state first; obtain approval for the exact change. An accepted operation is pending, not proof of connectivity. Poll the returned operation/resource on its in_progress flag, waiting next_check_seconds between reads: while in_progress is true its reason_code is what is awaited (reason_kind waiting, e.g. a queued or pending reason, or a control plane that has not answered yet), never an error; only in_progress false with reason_kind failure is a failure. Preserve reason_code. On transport uncertainty inspect state and reuse only the original key and unchanged request; never automatically retry.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
network_idYesExact lowercase UUID returned by an owned networking resource
idempotencyKeyYesIdempotency-Key for this exact change; preserve it and the unchanged body on uncertain recovery
expected_generationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.3.16

TDQS

A4.4/5.0
Behavior5/5

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

Substantially exceeds the annotations. It discloses that a retry may resume a failed deletion or settings change (the destructive dimension), the required networking:read/networking:manage scopes and that defaults do not grant them, backend-enforced ownership/feature/2FA locks, and the idempotent-key preservation rule on uncertain recovery. The polling contract (in_progress semantics, reason_kind, next_check_seconds) is behavioral detail no annotation conveys.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core action and scope, then layers permissions, polling, and failure semantics in a logical order. It is dense and long, but for a destructive, permission-gated, asynchronous retry most sentences carry operational weight rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Without an output schema the description still explains what comes back (an operation/resource with in_progress and reason_code) and how to interpret it, plus failure vs. waiting semantics and transport-uncertainty handling. Nothing an agent needs to call this destructive, idempotent retry safely is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 67% schema coverage the baseline is 3. The description does add meaning for two params — it says to preserve the current generation and the idempotency key on uncertain recovery — but expected_generation itself has no schema description and the description does not explain its format or what value to supply.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (retry) and object (the failed current network operation), plus the critical scope constraint 'only' and 'preserve its current generation.' This clearly separates it from siblings like retry_private_network_port and retry_network_security_policy 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.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete preconditions: inspect the failed operation first, read current capabilities and owned resource state, obtain approval for the exact change. It never names a competing sibling or an explicit 'do not use when,' but the context for invoking it is well specified.

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

Deploy Server

Other Tools