Product cards

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, but the description adds real behavior the agent cannot get elsewhere: there is no upstream batch endpoint, so this issues one spaced-out request per product (latency/rate-limit implication), and individual failures land in `errors` without aborting the rest. That partial-failure contract is exactly the kind of context annotations cannot express.

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?

Two short sentences: the first front-loads what comes back, the second front-loads when to use it and then the failure semantics. No filler, no repetition of the schema.

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 no output schema, the description usefully discloses one return key (`errors`) and the per-item fan-out behavior, which is the main thing an agent needs for a batch call. It stops short of describing the success payload shape or whether ordering matches the input list, which matters for a 10-item batch.

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% and the single `products` array is already documented down to accepted formats (UUID, /p/<id>/ path, full URL) and 1-10 bounds. The description only echoes the max-of-10 limit, adding negligible meaning beyond the schema, so the 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 resource and scope ('Short records ... for up to 10 products at once') plus the returned fields (name, price window, shop counts, category, brand), which is far more specific than a bare name restatement. It doesn't name the single-product sibling tb_product or otherwise differentiate itself from the other product-shaped tools in the list, so it stops short of a 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?

'Use to refresh a list of known ids' gives a clear selection condition: many ids, already known. However, it never states the inverse (use tb_product for one id, use tb_search when ids are not known) or any exclusions, so the agent must infer the boundary against siblings.

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