contabo_firewalls

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

Beyond the coarse readOnlyHint=false / destructiveHint=true annotations, the description discloses a runtime gate (write operations are rejected until CONTABO_ENABLE_WRITES=1) and granularizes destructiveness to specific operations ([DESTRUCTIVE] on delete and unassignInstance). The 'runs READ-ONLY' phrasing sits in tension with readOnlyHint=false, but since it is explicitly qualified as a default-state gate and the write operations are all enumerated, it reads as added context rather than a literal contradiction.

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?

Front-loaded with the dispatch rule, then a scannable bulleted operation list, then the read-only note and the reference pointer. Each block earns its place, though the read-only paragraph could be tightened slightly.

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?

For a nine-operation dispatcher with no output schema, the description covers the dispatch model, every operation's intent, per-operation destructiveness, the write gate, and where to find parameter docs. The main residual gap is that it never describes return shapes or pagination behavior for the list/get operations, which the absent output schema leaves undocumented.

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 description coverage is 100%, so the baseline is 3; the description earns above baseline by telling the agent that parameters are operation-specific and validated per operation, and by pointing to contabo_reference for full parameter documentation. It does not itself explain syntax of key fields (page/size/orderBy), so it adds structural rather than syntactic meaning.

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 names a specific resource (Contabo firewalls and their rules) and enumerates nine concrete operations, each a clear verb+resource pair (create, list, delete, get, update, updateRules, assignInstance, unassignInstance, listPresetRules). An agent can tell this apart from contabo_instances, contabo_snapshots, or contabo_privateNetworks purely from the resource scope and operation list.

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 explains the dispatch contract ('choose exactly one operation; every operation has its own parameter set') and routes the agent to contabo_reference for parameter docs, and it flags delete/unassignInstance as destructive. However it gives no sequencing guidance (e.g. list first to obtain firewallId before delete/get) and no explicit when-not-to-use or alternative-selection rules, leaving the per-operation choice implied by the labels alone.

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