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

Annotations already declare read-only, idempotent, closed-world, so the bar is low, yet the description goes far beyond: it explains the three match tiers, the fallback rule that similar_in_meaning only fires when no listing has every word, the nothing_found and no_full_match sentinels, ignored_words, and that prices are compared as stated and cross-currency at the day's rate. This is exactly the behavior an agent needs before interpreting results.

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?

Purpose is front-loaded in the first sentence, which is good, but the remainder is one dense paragraph that hops between match tiers, sentinels, language scoping, and three separate price/term rules. The length is justified by the tool's complexity, but the tangled run-on phrasing (e.g. the similar_in_meaning sentence) hurts scannability.

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?

There is no output schema, so the description must carry the return-value burden, and it does: it names the match field and its values, the nothing_found/no_full_match answers, understood.ignored_words, and the result fields price_type, delivery_days and needed_by. An agent has enough to call and interpret the tool without the 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 coverage is 77%, so the schema largely documents the 13 parameters itself. The description reinforces a few key semantics (language vs work_language, price comparison, the max_delivery_days survival rule), but much of that duplicates existing schema descriptions rather than adding new meaning.

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 opening sentence gives a specific verb and resource — search active listings by free text and filters — and immediately disambiguates the two listing kinds (offer vs request). It is clearly distinguishable from the singular get_listing and get_author siblings, though it never names them explicitly.

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 gives rich context for using results: read price_type before claiming a listing fits the budget, read delivery_days and needed_by because term-less listings survive the filter, and use work_language rather than language to filter by author language. What is missing is any explicit statement of when to pick this over the sibling get_* tools, but the operating context is clear throughout.

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