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

Annotations already mark this destructive and non-read-only, but the description adds substantial context beyond them: irreversibility ('LA CANCELLAZIONE È IRREVERSIBILE'), the two-phase plan_id/confirm flow, feed batching at 20,000 records, channel side effects (FBM default leaves FBA intact), and the note that SKUs never appear in the conversation. It also points to check_feed_status as the follow-up step.

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 is long, but every clause carries operational weight (threshold, rate-limit rationale, phase ordering, channel semantics, irreversibility, next step) and the critical scoping constraint is front-loaded. Dense rather than bloated, though slightly tighter phrasing could trim a few redundancies.

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 destructive, six-parameter, no-output-schema tool, the description covers the full lifecycle: when to use it, the two mandatory phases, what phase 1 returns (counts, FBA/FBM split), the confirmation requirement, irreversibility, and post-execution follow-up. No output schema exists, but the description describes the meaningful return artifact (the plan with counts) without duplicating a schema.

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, but the description adds cross-parameter meaning the schema cannot: skus bypasses the report and ignores channel, channel='FBM'/'ALL' have asymmetric deletion effects, plan_id comes only from phase 1, and confirm must accompany plan_id to actually execute. This clarifying workflow context justifies a bump over 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 (bulk-delete listings on an account) and explicitly distinguishes itself from the sibling delete_listing ('USA QUESTO, non delete_listing in ciclo'). The scope is further pinned down by the channel filter and the two-phase flow, so an agent can separate it from all siblings at a glance.

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 an explicit selection threshold ('più di qualche decina'), names the alternative to avoid and why (delete_listing is SKU-by-SKU and hits Amazon rate limits), and lays out the mandatory two-phase procedure with the user-confirmation gate between phases. Nothing about when to use it is left to inference.

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