aras_import_aml

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

With no annotations provided, the description carries the full burden of behavioral disclosure — and it does disclose the most critical trait: the tool can execute destructive actions. The fact that the dryRun is described as reporting 'quante azioni distruttive contiene' before executing suggests a safety mechanism that an agent must be aware of. However, there's no mention of idempotency, atomicity, partial-failure behavior, or what the return payload looks like after a real apply — significant gaps for a state-mutating import tool.

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?

Two dense, well-ordered sentences carry a meaningful amount of information with no filler. The most important information (what it does, its relationship to a sibling) comes first, followed by the safety-related dryRun behavior. The only reason not to give a 5 is that the compactness comes at the cost of omitting the execution semantics entirely (what happens after a real apply), and the definition could easily make room for that with a couple more words.

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?

This is a high-blast-radius tool; it can apply AML packages that contain destructive actions — yet it has no annotations, no output schema, and no description of post-apply behavior. An agent won't know whether the import is transactional, what the response shape is, or whether it should expect the tool to commit changes beyond the dryRun. For the safety value of the dryRun feature to shine, the definition needs to either declare those semantics or point to a doc resource. The gap is noticeable compared to the export sibling, making this a missed opportunity.

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 50%, and the description does add meaning to the `dryRun` parameter: it explains that it's the default, that it analyzes the package, and reports the count of destructive actions before executing. This goes beyond the schema's 'boolean, default true.' However, the description doesn't clarify anything about the `contenuto` format beyond what the schema already says ('Uno o più <Item .../>'), and there's no guidance on what the return value looks like in either mode (dry=true vs false). Reasonable but incomplete parameter-level coverage.

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 is precise about what the tool does: 'Applica un pacchetto AML' names the verb ('applica') and the resource ('pacchetto AML'). It immediately differentiates itself by stating it is 'l'inverso di aras_export_aml' (the inverse of aras_export_aml), making its relationship to siblings explicit. The dual-mode behavior (dryRun vs. execute) further clarifies the scope of the tool.

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?

The explicit naming of aras_export_aml as its counterpart effectively tells an agent when this tool is the right choice (importing/pushing a package) vs. when to use the sibling. The description clarifies the dryRun default and that it a) analyzes content and b) reports destructive action count before executing. It doesn't enumerate possible conditions where an import would be invalid or explain whether there are more appropriate state-changing siblings, but the inverse relationship to its export counterpart provides enough guidance to route an agent correctly.

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