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

Annotations declare readOnlyHint=true and openWorldHint=true. The description adds significant behavioral context: it uses a union of five portals, covers ~57,000 properties with listings seen in the last 10 days, and explains that only ~70% of listings publish common expenses, so the total is only shown when the same listing publishes both. It also outlines the return fields (link, median, neighborhoods, save/alert link) and the conditionality of expenses. This is rich disclosure beyond the annotations.

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 description is a long, dense run-on of multiple clauses, listing many filter categories that are simply repetitions of the schema's parameter descriptions. While the purpose is front-loaded and the structure flows from purpose to filters to output to alternative, it is far from concise. It could be condensed by referring to the schema for filter details and focusing on unique behavioral and usage aspects.

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?

Given the tool has 28 parameters and no output schema, the description is quite complete. It explains the aggregated sources, the recency (last 10 days), the coverage (~57k listings), the handling of missing expenses, the return data (rent, expenses, total when available, link, median, top neighborhoods, save/alert link), and explicitly names the alternative tool. An agent can understand what to expect and when to use this 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 description coverage is 93%, so most parameters already have detailed descriptions. The description summarizes filter categories (neighborhood, type, bedrooms, price, etc.) but does not add much per-parameter meaning beyond what the schema provides. For instance, it mentions 'TOTAL MENSUAL con gastos comunes' which maps to monthlyMaxUyu/expensesMaxUyu, but the schema already describes those. It adds minimal new semantic value.

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 clearly states the tool searches rental homes across Uruguay, aggregating multiple sources (Mercado Libre, InfoCasas, etc.), and lists a comprehensive set of filter criteria. It also explicitly distinguishes itself from the sibling tool rank_rentals_for_household by pointing to that tool for household-based ranking, so an agent can tell them apart without inspecting schemas.

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 explicitly says to use rank_rentals_for_household for ranking based on income and household moves, providing a clear alternative. It doesn't mention other search-related siblings (e.g., list_houses, get_rental) but the purpose is distinct enough. The description implies usage: whenever a user needs to find rental listings with multi-source filtering and aggregated results. Good but not exhaustive.

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