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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description adds genuine semantics beyond that: missing facts stay missing (no interpolation) and unlike tests/units are not conflated. That tells the agent how to interpret incomparable results, which no annotation covers.

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 tight sentences, front-loaded with what is returned, followed immediately by the interpretation caveat. No filler or repetition.

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 usefully characterizes the return ('source-scoped facts and full technical context') and its interpretation rules. It does not detail structure or language behavior, but safety is covered by annotations, so it is nearly complete for this tool.

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%: the 'products' parameter has an enum and min/max bounds but no description, while 'language' is documented in the schema. The description restates the 2-3 bound but adds no meaning about the product identifiers or language codes, so it does not compensate for the coverage gap.

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 (compare/return side by side) and resource (products), reinforced by the 2-3 count that matches the schema constraints. It implicitly separates itself from the single-item siblings like get_product, but never names an alternative explicitly.

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?

Usage is only implied: the 2-3 product count signals this is for multi-product comparison rather than single lookups. There is no explicit 'use this when...' or 'use get_product instead for single items' routing, leaving the agent to infer.

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