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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses conditional behavior that the agent cannot infer elsewhere: buyer guidance, materials, branding options and live product IDs only appear for reviewed collections (flagged via get_collections detailedGuidance: true), and priceLadder appears only for seven named collections. It also explains price semantics (AUD ex-GST at volume, MOQ stated separately) and locale gating of AU-only offers.

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?

Nearly every clause carries real information, but it is delivered as one sprawling sentence stitched together with em-dashes, semicolons and stacked parentheticals, so the two hard behavioral rules (reviewed-collection extras, priceLadder coverage) are buried mid-paragraph instead of front-loaded.

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 burden of describing returns and does so thoroughly, including the conditional priceLadder shape (cheapest per type/material at MOQ and at 100/250/500/1,000 units). Minor gaps remain: no mention of error behavior for an invalid or unreviewed slug, and no sense of response size or truncation.

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 100%, so the baseline is 3; the description still adds value by tying `slug` to its source of truth ('Works for every slug in get_collections') and by framing the result as an 'English/AUD reference' that the `locale` parameter shifts. It does not elaborate on the locale enum beyond what the schema already lists.

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?

Opens with a specific verb+resource ('Get a collection's live picks') and then enumerates exactly what a pick contains (named product, From price with MOQ caveat, URL), plus the extra blocks (FAQs, buyer guidance, priceLadder). It is clearly separable from get_collections (slug discovery), get_product, and get_quote (local currency), which are named inline.

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 tells the agent how to obtain a valid slug ('Discover slugs with get_collections'), when to prefer siblings ('use get_product or get_quote for local currency'), and gives concrete example briefs it suits. What it lacks is any explicit 'do not use this for X' or a warning about behavior when a slug is not a reviewed collection beyond the conditional clause.

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