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

Annotations already declare the safe read-only, idempotent, non-destructive profile, and the description goes well beyond them: it discloses the result cap (20), sort order (biggest discount first), return fields (price, regular price, discount, last day), the meaning of null (while stocks last), and the multi-buy semantics where the quoted price is for one piece. These are non-obvious behavioral traits an agent needs.

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 verb and resource, then moves efficiently through search behavior, return shape, and edge cases. Dense but every sentence carries information; the multi-buy clarification is slightly specialized but earns its place as a query caveat.

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 carries the burden of explaining return values and does so explicitly (fields, ordering, cap, null meaning). Combined with the geographic/currency scope note and multi-buy caveat, an agent has everything needed to call and interpret the 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 high at 80%, so the schema already documents most parameters. The description still adds meaning beyond it: that the query matches across languages with German/French/Italian names working best, that retailers can be restricted or left empty for all stores, and that language affects which retailers appear. These are genuinely additive hints rather than restatements.

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 (find/search) and resource (this week's promotions at named Swiss supermarkets), listing the exact retailers covered. It is clearly distinguishable from siblings like eini_create_meal_plan or eini_my_shopping_list, which are about planning and lists, not deal discovery.

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?

Provides clear in-tool usage context ('search by product', 'filter by store and category', 'leave empty for the biggest discounts overall') but never states when to prefer this tool over siblings such as eini_create_meal_plan or eini_my_shopping_list, nor any exclusions. Usage is implied rather than explicitly routed.

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