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

With no annotations at all, the description carries the full behavioral disclosure burden, and it does well: it reveals that reference listings are hidden from default browsing but counted in marketplace stats, that ratingAvg/ratingCount come from verified buyers, and that min_rating excludes unrated listings. It does not disclose pagination behavior or the overall result shape, and it mentions a 'price' parameter that is absent from the input schema, creating a spec inconsistency.

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 core purpose is front-loaded and each sentence adds dense specification information—filters, sort semantics, result provenance, special modes, and defaults. It is a single run-on paragraph and the paid/free explanation is slightly verbose, and the sort/price inconsistencies with the schema add mild ambiguity, but there is almost no filler; nearly every clause carries usable information.

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 9-parameter tool with no annotations and no output schema, the description covers an unusually high amount of behavior: defaults, hidden reference samples, rating scheme semantics, and the two price-mode catalog behaviors. Remaining gaps are the exact result format, how category/vertical slugs are resolved (only referenced via the schema), and defaults for limit/offset pagination.

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 78%, so the description only needed to add on top—and it does: it defines sort meaning (quality is a Bayesian-weighted buyer score, trust is seller reputation), the samples filter's three modes, the paid/free listing catalog split, and specifies that min_rating drops listings without ratings. The additions are genuinely informative, though the advertised 'price' parameter is missing from the schema and the description's sort list ('price') does not exactly match the schema enum ('price_asc'/'price_desc').

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 with scope: "Browse and search listings for sale by other agents across all categories." It further names the distinct capabilities (category/vertical/type filters, sort modes, price and samples filters) that separate it from sibling tools like sell_data, update_listing, preview_listing, and deactivate_listing. An agent can immediately identify this as the marketplace discovery/browse 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?

Provides clear context for when to use different modes: price='paid' vs 'free' vs default 'all', samples='only' to fetch reference listings, and min_rating to restrict to well-rated listings. However, it never states when not to use the tool or names alternatives (e.g., preview_listing for inspecting a single listing, buyer tools for purchase), so exclusions are implied rather than explicit.

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