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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower; the description still adds real behavior beyond them by stating that consent, verification, review, entitlement and field freshness are re-checked on every call, meaning results are never stale or cached. The priceObservedAt/priceProvenance versus lastObservedAt sentence discloses a subtle retention rule that an agent could not otherwise know. It stops short of describing response shape or result limits.

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?

Three tightly packed sentences, front-loaded with the purpose and pagination rule before the heavier freshness and price-provenance caveats. The final sentence is dense and slightly jargon-heavy, but given the absence of an output schema it earns its place.

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 six-parameter, low-coverage, no-output-schema search tool, the description covers pagination and price-field semantics well but leaves the filtering parameters and the overall result structure unexplained. An agent could call it, but could not confidently construct city/query/currency/maxPrice combinations from the text alone.

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 description coverage is only 17% — just catalogId is documented — so the description carries most of the burden, and it addresses only the cursor parameter via "Follow nextCursor." It adds nothing about city versus query, what currency applies to, or how maxPrice interacts with currency, leaving four of six parameters semantically bare.

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?

"Search published records in this catalog" gives a specific verb (search) and a bounded resource (published records within a catalog), which is more precise than a bare name restatement. It does not explicitly contrast itself with the closest siblings (search_auctions, search_findestate_properties, compare_properties), so an agent must infer the boundary from the word "catalog" alone.

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?

"Follow nextCursor for later pages" gives concrete in-flow guidance for pagination, and "published records in this catalog" implies the scope of use. However, there is no statement of when to prefer this over search_findestate_properties or search_auctions, and no exclusions or prerequisites beyond the catalogId implication.

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