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

Adds real context beyond the annotations: it explains the readOnlyHint=false by disclosing that the call 'uses one read and saves the result in the user's Puley history', and it flags latency for several portals (Domain about 30-50 s, Funda about a minute, SeLoger and Immobiliare slower). It also describes the listing payload (price, beds, baths, size, address, listed/reduced dates, Zestimate on Zillow) which is valuable given there is no output schema. Error behavior and failure modes are not covered.

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 facts are front-loaded and nearly every clause carries routing information an agent needs, but the sixteen portal entries are delivered as one dense semicolon-separated block rather than a scannable list or table. The repeated 'country XX' pattern and per-portal examples make it long and hard to parse in a single pass.

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 five-parameter open-world aggregation tool with no output schema and no annotation-level detail, this is close to complete: input formats, currency handling, return fields, latency warnings, and the history side effect are all stated. The gaps are min_beds semantics and any mention of failure or empty-result behavior.

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 0%, so the description must carry the parameter burden. It covers place in depth (per-country formats and examples), country via the per-portal ISO codes, max_price ('in the local currency, 0 for any'), and mode ('buy or rent'). It never explains min_beds, and only hints at it obliquely ('rooms, not bedrooms' for immowelt), leaving one of five parameters undefined.

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?

A specific verb+resource ('Homes for sale or rent, newest first') with an exhaustive enumeration of the source portals per country, so an agent knows exactly what corpus is searched. It never names a sibling (find_stays, find_cars, search_classifieds, search_marketplace) to draw the boundary, so sibling differentiation is left implicit rather than stated.

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?

Strong conditional guidance: it tells the agent which portal applies to which country, what location format each expects (e.g. 'Bondi, NSW' for Domain, 'Annex, Toronto' for Zolo, 'SW4' for Rightmove), and routes Quebec places to Centris. It stops short of stating exclusions — nothing says when to prefer find_stays or search_classifieds instead — so it is clear context without explicit negative routing.

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