Search used-phone ads

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description still adds non-inferable behavior: seller names and phone numbers are stripped from results, and listings are unverified user content that should not be treated as ground truth. It stops short of describing result volume, total counts, or pagination end conditions.

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?

The purpose and scope lead, followed by the privacy caveat, the price_note quirk, and the sibling hand-off — a sensible order with no filler sentences. The price_note aside is slightly parenthetical and interrupts the flow, and the parenthetical field list is ambiguous about whether those are filters or returned fields.

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 12-parameter tool with no output schema, the description does meaningful work: it sketches the ad record contents, flags stripped contact data, and explains the non-numeric price field an agent would otherwise misread. It still omits the shape of the list response (items, totals, page bounds), which matters more here precisely because no output schema exists.

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%, with enums and defaults documented for days, kind, sort, condition, prices and name_contains, so the schema carries the parameter burden. The description only echoes the filterable dimensions (price, condition, city) and explains price_note values, which is marginal added meaning over the schema. Baseline 3 applies.

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 (search) and resource (used and new phone ads posted by users on Mobile.ir), and names the concrete content domain with the filterable/returned attributes in parentheses. It also routes to the sibling mi_used_ad for the single-ad case, so an agent can distinguish this from the detail tool 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?

"Open one ad with mi_used_ad" gives an explicit alternative for the drill-down case, and "Ads are unverified user content" tells the agent how to treat results. However, with 16 siblings including mi_search, mi_find and mi_shop_prices, the description never says when to prefer this classified-ads search over retail shop prices or the general search tools, leaving the most likely confusion unresolved.

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