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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior. The description adds substantial context beyond that: coverage limits, which grocery categories are checked, what the return listings contain, price caveats, inventory freshness, and the fact that a listing is not a later-day guarantee.

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?

The description is front-loaded with the use case and then scope, exclusions, and fallback behavior, so it is easy to scan for the key decision. It is very dense and somewhat sprawling because of the retailer list, grocery-category list, and multiple example phrases, though most of that detail is scope-critical.

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 nine-parameter search tool with no output schema, the description covers what it returns, coverage limits, data freshness, exclusions, and empty-filter fallback behavior. An agent has enough information to decide when to call it and how to populate the optional filters.

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 already 100%, so the schema documents each field. The description still adds important invocation meaning: only include size, fulfillment, max_price, or availability when the user asked; empty filters should be dropped; size is never dropped; and town or mall names must be mapped to a metro or ZIP.

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 opening sentence gives a specific verb, resource, and scope: finding a product in stock near a place, who has it, and stock near a city or ZIP. The boundaries around covered stores and excluded use cases make it clearly distinct from a general product or location search.

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 gives explicit when-to-use examples plus a detailed when-not list covering online-only shopping, restaurants, uncovered areas, unlisted chains, reserving items, and future availability promises. However, it does not name the sibling tools (for example, list_locations) as alternatives for resolving locations, so alternative-tool routing is left implicit.

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