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

Consistent with readOnlyHint=true ('solo lettura'), and adds substantive traits the annotations cannot convey: the plan expires after 24 hours, the return payload is plan_id plus a per-SKU before→after preview, and needs_review means residual words in manual_review that require a human decision. Also discloses the hard constraint 'MAI parole nuove' and the 250-byte generic_keyword cap.

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 purpose and the read-only marker, then the algorithm, then the return contract, then the mandatory preview rule. Dense and mostly earned, but the long parenthetical with the 250-byte/duplicate rules and the mid-sentence 'o alla descrizione' make it a heavy single block rather than cleanly segmented.

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?

With no output schema, the description carries the return contract and does so well (plan_id, preview, status values and their meanings), plus the plan's 24-hour lifetime. The gap is minor: it never says what happens for SKUs that cannot be shortened at all, nor how the preview is paginated or sized for large catalogs.

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 coverage is already 100%, so the baseline is 3; the description goes further by explaining the interaction between new_titles (overrides automatic truncation), original_titles (only relocates lost words, keeps current title), and include_bullets=false (unrelocated words go to manual_review). It does not add anything for skus, limit, or account_id beyond the schema.

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 and resource in the very first words: a read-only planning step that shortens titles to 72 chars while preserving SEO, and that relocates lost keywords. It is clearly distinguishable from apply_title_seo_batch (the execution step) and from title_seo_status/rollback by the 'passo 1' framing.

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 explicit operational routing: show the preview to the user before calling apply_title_seo_batch, and pass original_titles when the title was already trimmed so only lost words are relocated. It does not mention when to use title_seo_status or title_seo_rollback instead, so the alternative-routing is not fully exhaustive.

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