Query feed products

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

Beyond the readOnly/openWorld annotations, it discloses the response shape (total_count and matched_count), which fields are absent from results, and that filtering on those absent fields is refused rather than silently ignored. That refusal behavior is exactly the kind of detail an agent cannot 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?

Three tightly packed sentences with the defining scope claim front-loaded, and no filler. The 'MEASURED:' prefix is slightly jarring in prose but efficiently signals verified behavior, so the wording still earns its place.

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?

No output schema exists, and the description covers the key return facts (counts, missing fields) plus the pre-ad-group preview workflow. It leaves pagination and limit behavior unaddressed, which is a minor gap for a three-parameter read tool.

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 only 33% schema description coverage, the burden falls partly on the description, and it does contribute a real filtering constraint (availability and group_id cannot be filtered on). However it says nothing about feed_id semantics or the limit parameter beyond what the schema encodes, so the compensation is partial.

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 (products in a feed) and immediately disambiguates ownership: 'OpenAI holds in a feed (its copy, not Shopify's)'. That distinguishes it from update_feed_products and lets an agent know it is reading a mirrored catalog rather than the source system.

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?

Explicitly names two use cases: picking products for a campaign and previewing a product set before creating an ad group. It does not state when to avoid it or name a specific alternative, which keeps it short of a 5, but the intended call context is clear.

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