Skip to main content
Glama

Retire network security policy

retire_network_security_policy
DestructiveIdempotent

Remove a VPSnet network security policy after its server ports are gone, with explicit user approval and polling for each affected network.

Instructions

Retire the policy only after its server ports are gone. Removing firewall policy requires explicit user approval. Poll get_network_security_policy for each affected network (policies[].network_id); these receipts are not generic network operation IDs. 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
project_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

A4.3/5.0
Behavior5/5

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

The annotations already declare destructive, idempotent, and open-world behavior, but the description adds substantial context beyond them: explicit user approval, backend enforcement of ownership/feature availability/2FA locks, pending-versus-failure semantics for accepted operations, polling on in_progress with reason_code/reason_kind, and idempotent recovery rules on transport uncertainty.

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?

The description is front-loaded with purpose and approval requirements, and almost every sentence conveys operational guidance needed for a destructive, asynchronous tool. It is dense but largely earns its length, though there is some redundancy around approval and idempotency key handling that keeps it from being maximally concise.

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

Completeness4/5

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

For a complex destructive tool with no output schema, the description covers the important return-state semantics: polling the operation/resource, interpreting in_progress and reason_kind, and preserving reason_code. It is missing an explanation of expected_generation and could clarify what 'server ports are gone' means, but overall it is substantially complete.

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?

Schema description coverage is 75%, and the description reinforces idempotencyKey handling but mostly repeats what the schema already says about preserving the key on uncertain recovery. It does not explain expected_generation, which is the parameter lacking any schema description, so it does not fully compensate for the remaining coverage gap.

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?

The description opens with a specific verb and resource: 'Retire the policy only after its server ports are gone,' and clarifies that this is a firewall policy removal requiring approval. It also points to get_network_security_policy for related reads, giving enough context to distinguish this tool from generic network operations.

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?

It states a clear precondition ('only after its server ports are gone') and required permissions ('networking:read' vs 'networking:manage'), and says to read capabilities and obtain approval first. However, it does not explicitly name sibling alternatives such as retry_network_security_policy or when to choose those over this operation.

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