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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuinely new framing: results are the brand's own source-backed position, deliberately kept separate from independent proof — a crucial caveat about output bias that annotations cannot convey.

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?

Two sentences, zero waste. What the tool returns is front-loaded and the routing caveat follows immediately. Nothing extraneous and nothing buried.

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 still sketches the return shape (comparison pages containing a source-backed position separate from independent proof). The one remaining gap is that it does not warn that at most three competitors can be passed at once.

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?

One parameter with 0% schema description coverage, so the description must compensate. It conveys that a list of named alternative brands is expected, but omits the important maxItems=3 constraint and never references the fixed set of allowed brand identifiers in the enum.

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: returns IMPOSSIBREW's published comparison pages for named alternative brands. This is clearly distinct from product-level comparison siblings, though those siblings (compare_beers, compare_pack_value) are never named, so differentiation must be inferred.

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?

The second sentence draws a clear boundary: live prices and availability come from the product tools, so an agent knows not to use this for pricing. However it never explicitly names the alternatives (compare_beers, compare_pack_value, get_product), leaving the routing to inference.

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