datasets_doordash_stores_search

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

With no annotations, the description carries the full burden and does so exceptionally: it discloses field provenance (Explore vs hydration) and that un-hydrated stores may be missing contact/address/coordinates, warns that display_status/asap/pickup fields are point-in-time PICKUP observations rather than durable capabilities, and flags best-effort coverage with a 40-store-per-call Explore cap and a 10,000-result offset window. These are exactly the caveats an agent needs to interpret results honestly.

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, and every sentence carries substantive information (provenance, caveats, filter list, pagination). It is a dense block that could be broken up, but there is little wasted text and no 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?

For a 17-parameter tool with no output schema and no annotations, the description is strong: it covers the data model, missing-field behavior, filter dimensions, sort semantics, and both pagination modes. It stops short of describing what a returned result contains beyond next_cursor and the field groups, but the coverage is adequate for correct invocation.

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%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains that sort=relevance ranks by text-match score when q is supplied and falls back to store name otherwise, and that cursor tokens must be reused with the same filters and sort. This clarifies non-obvious interaction between parameters rather than restating them.

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 and resource ('Search the DoorDash store directory' / 'merchant-location directory, dataset id doordash-stores') with rich detail on how the dataset is built. An agent immediately knows this is a full-text/filtered store search. It does not, however, explicitly differentiate itself from the obvious siblings datasets_doordash_stores_nearby, datasets_doordash_stores_facets, or datasets_doordash_stores_item.

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 operational guidance such as 'Use pagination=cursor and the returned next_cursor to enumerate beyond the 10,000-result offset window' and explains that sort=relevance behaves differently with and without q. But it never states when to prefer this tool over the nearby/facets/item siblings or what conditions should route the agent elsewhere, so usage is only implied.

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