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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety behavior is covered. The description adds genuinely useful behavior beyond that: the corpus is pre-indexed text, single-datasheet answers are 'closest excerpts' with page numbers, and category scans return an exact product list with one excerpt each. No output schema exists, so this return-shape detail is doing real work.

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?

A single dense sentence, but well front-loaded: the primary ask-a-datasheet mode comes first, the scan alternative second. Every clause carries content; only the repeated 'and get...' construction adds mild redundancy.

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 4-parameter, dual-mode, closed-world tool with no output schema, the description covers both modes and roughly what each returns. It still leaves gaps an agent needs: that product_id is the single-datasheet selector, that category is required for the scan path, and that no parameters are formally required, so an under-specified call is possible.

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 50%, so the description must compensate. It does explain q and the term+category pairing implicitly, and its 'exact term' note aligns with the schema's 'exact word/phrase' wording, but product_id is never explained and category's role as a mode selector is only implied by the phrase 'of a category'.

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?

The description states two concrete verbs (ask/get excerpts vs. scan/list products) against named resources (a single datasheet, all datasheets of a category). An agent can tell what the tool does, though it never contrasts itself with close siblings like search_datasheet_facts or get_datasheet_digest.

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?

It clearly routes the agent between the two modes by naming the parameter combinations that select each (q for one datasheet; term + category for a category-wide scan). It stops short of stating exclusions or when to prefer a sibling search tool instead.

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