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

Annotations already declare readOnly, idempotent and non-destructive, so the bar is lower; the description still adds useful behavior: records are 'full live' reads, the batch size is 1–10, and missing records return per-number errors rather than failing the whole call. No auth or rate-limit context, which keeps it from a 5.

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 use condition, followed by scope, return fields and the negative case. Two sentences plus one clause, every one carrying information an agent needs to select and call the tool.

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 single-parameter lookup with an output schema and full annotation coverage, nothing essential is missing: trigger, exclusion, batch limit, returned fields and partial-failure behavior are all present.

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% and already documents the 4–8 character pattern, the 1–10 array bounds and an example ('27024'). The description's '1–10 recall numbers' restates the schema rather than adding new semantics, 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 verb and resource: 'Reads full live records for 1–10 recall numbers', plus the fields returned (hazard, remedy, contact, retailers, units, UPCs, image links). It implicitly separates itself from search_recalls by requiring recall numbers, but never names the sibling to make the split explicit.

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?

Opens with an explicit trigger ('Use this when the user wants cpsc recalls, a recalled products list, or is this product recalled and has a recall number') and adds a real exclusion ('Do not use for recalls outside consumer products'). It stops short of routing the agent to search_recalls or check_inventory_for_recalls when the user lacks a recall number.

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