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

Annotations already cover read-only, idempotent, closed-world and non-destructive, so the bar is lower, yet the description adds real domain behavior: last_human_review and last_price_check are separate facts, the lowest known total is scoped only to offers PostThisDeal checked, and commission never influences ranking. These are meaningful integrity constraints an agent cannot infer from structured fields. It does not state what happens when the ID is invalid or the comparison is unpublished, which keeps it below a 5.

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 core purpose is front-loaded, but the single sentence becomes a dense run-on field inventory (evidence status, last automated check, price-change flag, end dates, verdict) that largely duplicates what the output schema already declares. The trailing ranking/commission caveats earn their place; the field list does not.

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, the description need not enumerate return fields, and it compensates with the behavioral notes on review dates, checked-offer scope, and commission neutrality. The main gap is error/unpublished-ID behavior. For a simple single-ID read against rich annotations and an output schema, it is close to complete.

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% for the single comparison_id parameter, and the schema already says it comes from search_comparisons. The description adds only the indirect implication that the ID must reference a published comparison. Baseline 3 is appropriate when the schema carries the parameter burden.

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?

Opens with a specific verb-and-resource framing ('One published comparison') and enumerates what the payload contains: product, approved offers, seller, price, shipping, known total, evidence status, check timestamps, verdict. It is clearly distinct from list-style siblings like search_comparisons. It stops short of explicitly naming the sibling it replaces, but the singular scope is unmistakable.

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: 'One published comparison' signals single-record retrieval, contrasting implicitly with search_comparisons. There is no explicit when-to-use statement, no note on what to do if the ID is unpublished or missing, and no routing to get_offer or verify_offer for follow-up detail. The schema's 'From search_comparisons' does the routing work the description omits.

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