Search ads

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

Goes well beyond the readOnly/idempotent/openWorld annotations: it discloses promoted older ads appearing in the first 1-3 rows, that ordering is newest-first, that unsupported category filters are returned in 'ignored', and that an empty Persian query is retried once with folded letters. These are non-obvious runtime behaviors an agent could not infer from annotations or schema.

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 with the core purpose, then a tight second paragraph of behavioral facts. The second paragraph is clause-heavy, but each clause carries distinct information (age_h, image, suspect_price, ordering, cursor, ignored, retry), so little is wasted.

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 20-parameter tool with no output schema and nested filter objects, the description does the heavy lifting on return-value semantics (age_h units, image gating, suspect_price 'outlier' rule, next_cursor), deferring only the card field list to server instructions. The remaining gap is that it doesn't explain the ignored-filter contract's impact on results or pagination limits with `pages`.

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?

With schema description coverage at 100%, the baseline is 3, but the description adds relational meaning the schema does not: 'image comes only with thumbnails' ties two parameters together, and it clarifies cursor semantics by mapping 'next_cursor' from a prior call into the cursor param. Dense param docs are still carried by 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?

Opens with a specific verb+resource+scope: 'Search Divar ads in one or more cities by category, text and filters', plus the output shape ('compact cards, prices in Toman'). This is clearly distinguishable from siblings like dv_count, dv_cheapest, or dv_nearby 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?

Usage is implied through the 'Next: dv_post, dv_compare, dv_cheapest, dv_market' follow-up list and the cursor-continuation note, but the description never states when to prefer dv_search over the many overlapping siblings (dv_count, dv_find_deals, dv_place_search) or any when-not conditions. Adequate but leaves the routing decision to inference.

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