Export ads

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

Annotations already establish readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuinely useful behavior: the payload arrives as text in `data` and the caller must write the file itself, missing prices are emitted as empty fields, and the exact column set. That is real disclosure beyond structured data, though it says nothing about size limits or truncation.

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?

Purpose is front-loaded in the first clause, followed by the essential operational note about `data` and the file-writing responsibility. The column enumeration is compact and earns its place because there is no output schema to describe the shape.

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 18 optional parameters, nested `filters`, and no output schema, the description carries the return-shape burden and does so by enumerating columns and flagging empty prices. It does not touch on output size, pagination interplay between `limit` and `pages`, or the `ignored` key mentioned in the schema, leaving minor gaps.

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% across all 18 parameters, so the schema fully documents city, limit, pages, format, filters, etc. The description adds no parameter-level meaning beyond pointing at dv_search's argument set, which is the expected baseline when the schema does the heavy lifting.

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?

States a specific verb+resource (ads of a search exported as CSV or JSON lines) and names the output medium, which clearly separates it from dv_search's inline results. It even lists the emitted columns. It stops short of explicitly contrasting itself with dv_search beyond noting the shared arguments, so it is not a full 5.

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?

"Same arguments as dv_search" plus "ready to save to a spreadsheet or analyse" implies when to reach for this tool over the search sibling, but there is no explicit when/when-not statement or named alternative. The reader must infer that dv_export is the file-producing counterpart of dv_search.

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