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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real value beyond them: deduplication to one best offer per vendor, sort order, the explicit tie-break that blends and unpriceable products sort last, and the price encoding as integer minor units plus display strings.

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, no waste, and the most decision-relevant facts (scope, dedup rule, sort order) are front-loaded before the price-format detail. Every clause carries information.

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 an output schema present and a single fully documented parameter, the description need not explain return fields. It covers ordering, dedup, and edge cases; the only gap is what happens for an unknown or unpublished slug, which is only hinted at by 'published'.

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 an inline example ('retatrutide'), so the baseline is 3. The description nudges meaning by specifying the compound must be 'published', a constraint the schema does not express, which slightly raises the score.

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 resource (live offers for one published compound) and the exact shape of the result: one best offer per vendor, sorted by price per mg ascending. That level of specificity distinguishes it cleanly from get_compound, list_vendors, and search_compounds, which do not aggregate offers.

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 'for one published compound' – the agent infers it needs a compound slug and wants vendor pricing – but the description never says when to prefer this over list_vendors, nor any prerequisites or exclusions. Adequate but leaves routing to inference.

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