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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, and the description adds materially: approximate payload size (~15 KB), a 60-reports-per-hour-per-caller quota shared across four other tools, and a note that `contact_owner_url` opens a letter to the owner. What it omits is error/partial-data behavior, e.g. what `tiles` returns when a section (crime, air quality) is unavailable.

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-loaded headline followed by two compact groupings (brief facts, then the nine tiles), then cost, then routing advice, then quota — a sensible information order. The nine-item tile enumeration is long but each entry carries distinct content, so there is little filler.

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 full burden of explaining returns and does so section by section, including the derived semantics of response likelihood (High = listed for sale and owner-occupied). Combined with quota and size disclosures, an agent has everything needed to decide to call it and to interpret the result.

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?

The single parameter `akey` is fully documented in the schema (hex pattern, length bounds, provenance from search_addresses), so the schema does the work. The description never mentions `akey` at all; its detailed naming refers to response fields (`home`, `tiles`, `contact_owner_url`), not to the input, so it adds no parameter 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?

Opens with a precise verb+resource statement ("Everything GetMovely knows about one home in one call") and then decomposes the payload into `home` facts and `tiles` sections, naming exactly what each contains. An agent can distinguish this aggregate tool from single-fact siblings without inspecting any schema.

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?

Gives an explicit selection rule tied to a cost signal: ~15 KB payload, so use get_address, sale_history, energy_performance or price_check "when one part is enough." It also states the rate-limit budget and that the limit is shared with those same tools, which tells the agent when to spend the call carefully.

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