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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so the safety profile is covered; the description adds non-obvious behavior: it reads live recall data, emits XLSX and CSV files, caps at 1–100 items, and carries accuracy caveats ('word matches require verification', 'models written with spaces can be missed'). It stops short of covering runtime or what happens to unmatched items, keeping it below 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?

Four sentences, front-loaded with the usage trigger, then behavior, then caveats, then exclusions. No sentence is redundant with another or with the structured 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?

An output schema exists, so return values need not be described; annotations cover the safety profile. The description supplies the remaining operational context (live data source, file outputs, item limits, scope exclusion) that an agent needs to select and invoke this tool correctly.

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 schema already documents items, UPC/brand/model/product, and recalled_since_year. The description still adds useful matching semantics beyond the schema: word-based matching needs verification and spaced model numbers can be missed, which tells the agent how to interpret the text fields.

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 ('check my inventory for recalls', 'run a resale recall check') and adds concrete output behavior (XLSX/CSV screening files). It is clearly distinguishable from search_recalls and get_recall_details, which are lookup/detail tools rather than batch inventory screening.

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 clause ('Use this when the user wants to...') listing three paraphrase variants of the intent, and closes with an explicit exclusion: 'Do not use for food, drugs or vehicle recalls.' Both when-to-use and when-not-to-use are present.

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