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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the bar is lower. The description still adds real context not present in the structured fields: the result cap (up to 20), the fact that each result carries an id intended to be passed to fetch, and the UK/participating-agent scope. It stops short of describing ranking, pagination beyond the cap, or behavior when no results match.

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?

Four short sentences, front-loaded with the core action, then the input shape with examples, then the return contract and the fetch chaining, then the sibling disambiguation. Every sentence carries distinct information and none is redundant with the schema or annotations.

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?

An output schema exists, so return values need not be spelled out, and the description still covers the result count and the id-to-fetch handoff. With a single fully described parameter, full annotation coverage, and explicit sibling routing, an agent has everything needed to call this correctly on the first attempt.

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 coverage is 100% and there is only one parameter, so the baseline is 3. The description exceeds that by explaining the query's expected syntax and content (plain English including a place, with example phrasings like "flats to rent CT20"), which meaningfully constrains how an agent should phrase the string. Only the 200-character limit is left to the schema.

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 and resource ("Searches homes for sale or to let from participating UK estate agents"), defines the input shape ("one plain-English query"), and gives concrete examples. It also explicitly contrasts with the sibling search_listings, which accepts the same filters separately, so an agent can pick between the two without opening a 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?

It names the alternative (search_listings) and gives the selecting condition: this tool is "made for apps that use standard search and fetch tools (ChatGPT deep research)." It also states a coverage constraint (name a town, outcode or postcode). There is no explicit "do not use this when..." clause, but the routing information is clear enough for an agent to choose correctly.

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