auto_optimize_listings

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

With only openWorldHint declared, the description carries the full disclosure burden and does so richly: it states DEFAULTS TO DRY-RUN, that applying only ever archives (never deletes, never goes live), that archiving is restricted to genuinely inert listings, and that with no demand data the proposal is 'review' and nothing is applied. This is exactly the safety framing an agent needs for a potentially destructive mutation.

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?

The safety-critical constraints are front-loaded and the prose is dense with useful content rather than filler. It loses a point for the trailing stray artifact '[#170c11]', which is noise with no informational value.

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 and only openWorldHint annotation, the description supplies the mutation semantics, default mode, and fallback behaviour an agent needs. The main remaining gap is the meaning of the scope enum values, which matters for selecting rather than merely invoking the tool.

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 only 25%, and the description compensates well for dry_run (confirming the default and what happens when false) but not for the scope enum values (underperformers/out_of_date/all) or for workspace/store_uuid, which are undocumented in both schema and prose. Genuine added value on one parameter against clear gaps on the others.

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 verb (propose/apply) and resource (optimizations across listings), and implicitly distinguishes itself from sibling archive tools by explaining that a seen-but-unbought listing is fixed rather than archived. It is clear what the tool does, though it never explicitly contrasts itself against near neighbors like listing_changes or diagnose_tiktok_listings.

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?

Usage context is implied rather than stated: the tool operates 'across listings' with a scope enum, and dry-run is the default. There is no explicit when-to-use/when-not guidance relative to siblings such as archive_product, sync_to_channel, or listing_changes, so an agent must infer routing from the behavioural prose.

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