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

Annotations already declare readOnly/openWorld=false/idempotent, so the safety profile is covered. The description adds genuinely non-structured behavior: certain queries yield an extra projects[] field (Allmannsdorf 44 WE), and contacts must be surfaced only as links for a human rather than exposed directly. That last constraint is an important agent-behavior rule beyond what the schema or annotations provide.

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?

Front-loading the verb+resource is good, and three sentences is a reasonable size. However, the 'projects[] (Allmannsdorf 44 WE)' fragment is telegraphic and refers to a field absent from both the input schema and any output schema, forcing the agent to guess. It earns its place less than the surrounding routing advice.

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?

With no output schema, the description carries the burden of describing returns; it only hints that projects[] may appear for certain queries and says nothing about result shape, ordering, or the default/max limit behavior (which the schema does cover). The next-step workflow (get_flyer, get_contact) is a useful addition. Adequate but with clear gaps for a 7-parameter, output-less search 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 100%, so every parameter (q, type, limit, rooms, location, min/max_price_eur) is already documented with examples — the baseline is 3. The description adds no syntax or filtering semantics beyond the schema; its 'projects[]' and 'Allmannsdorf 44 WE' notes describe results, not inputs, and reference a field that appears in no parameter.

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 states a specific verb+resource — 'Kaufangebote (Konstanz/Bodensee) suchen/filtern' — so an agent knows this is a search over purchase listings in a fixed region. It distinguishes itself from get_listing/get_flyer/get_contact by framing itself as the entry point. The cryptic 'projects[]' clause and the embedded workflow note slightly muddy the core statement but don't obscure the purpose.

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 explicit routing: search here first, then 'get_flyer + get_contact', and warns that no 'Flyer' search word is needed — implying a common misuse. It also states a condition under which results additionally contain projects[] (q/location = Neubau/Allmannsdorf/Wohnung Konstanz). No explicit when-not-to-use-this-tool statement, so it stops short of a 5.

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