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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real behavioral context the annotations cannot: each result is scoped to the product version on run_date and the stated plan, and later versions inherit nothing — a critical caveat for interpreting results correctly. It omits pagination behavior despite limit/cursor params.

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?

Front-loaded with the core purpose in the first clause, followed by query guidance and then the important scoping caveat. Two sentences with little waste, though the inline enum list is dense enough to slightly strain readability.

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 should characterize return values more than 'what we observed.' It conveys the semantic scoping well but never sketches the shape of a returned observation (fields like run_date, plan, task) nor pagination behavior for a 5-param list 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 0%, so the description must carry the load. It does document the result parameter's six allowed values (an enum the schema lacks) and clarifies that query means task words and product_id is a product identifier. But limit and cursor are entirely unexplained, leaving conventional-but-unstated pagination semantics.

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 states a concrete purpose: returning first-hand observations from running products, searchable by task words, product id, or result. It is more than a tautology and tells the agent what data it holds. However, it never differentiates itself from the sibling tool get_evidence, leaving the agent to guess which evidence tool to call.

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?

'Search by task words, product id or result' describes how to query, which implies usage, but there is no explicit statement of when this tool is preferable to get_evidence or the other evidence-adjacent siblings. No exclusions or prerequisites are given.

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