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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's added value is the null-when-absent contract and a sketch of the returned payload (why/impact/steps plus agent prompt). That is meaningful behavior beyond the annotations, though it says nothing about what happens with an invalid productKey.

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?

One sentence, front-loaded with the resource and scoped to a single product, with no filler. The parenthetical payload summary is dense but earns its place by describing the return shape.

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 burden of describing returns and does so adequately, including the null case and the payload contents. Minor gaps remain around failure behavior for a bad key, but an agent has enough to call it correctly.

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% and the single productKey parameter is documented in the schema with a pointer to list_products. The description only says 'for one product', adding no format or resolution detail beyond the schema, so the 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 states a specific verb+resource: retrieving the stored AI bottleneck analysis for a single product. It implicitly separates itself from generation-style siblings by emphasizing 'stored' and 'null if not run yet', though it never names an alternative tool outright.

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?

The phrase 'or null if not run yet' hints that this only reads pre-computed analysis and something else must produce it, but no sibling (e.g. get_fix_cards, get_insights, check_launch_readiness) is named as the alternative. Usage is implied rather than stated.

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