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

Annotations already declare read-only, idempotent, non-destructive and closed-world, so the baseline bar is lower. The description still adds real behavior: values are normalized into the property's canonical unit and mismatched measurement conditions are never averaged, which materially affects how an agent interprets results.

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?

Three tight sentences, front-loaded with what the tool produces, then the canonical-unit guarantee, then the non-averaging caveat. No sentence repeats the schema or the title.

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 return-shape burden and does so: per-material value, conditions and source, plus value_canonical. What's left unsaid — ordering, behavior for unknown properties or properties lacking canonical units — is minor for a read-only comparison 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 100%, with both parameters documented (including an example property and 'Ids from search_materials' with 2–12 bounds). The description adds no parameter-level detail beyond implying 'property' is singular and 'materials' plural; baseline 3 applies.

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 gives a concrete verb and scope: it lines up several materials on a single property and returns each value with conditions and source. That clearly distinguishes it from single-material siblings like get_material, though no sibling is named 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 implied by 'line several materials up on one property' — a multi-material, single-property read — but there is no explicit when-to-use vs. when-to-use-an-alternative guidance. The note that differently-conditioned values are listed separately rather than averaged is useful expectation-setting rather than routing guidance.

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