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

Annotations include readOnlyHint=false, idempotentHint=false, and destructiveHint=false, but the description adds valuable context: it maintains a stateful baseline (first run creates baseline and says so) and costs $0.05 per call. This goes beyond the annotations without contradicting them, though it does not detail auth or rate limits.

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 description is a single, front-loaded sentence stating exactly what the tool does, followed by a brief pricing note. No wasted words; it is immediately scannable and actionable.

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?

The description lacks clarity on the output granularity: it says 'products' but the websites parameter description mentions 'store newly added' and 'price range / catalog size / estimated revenue band shifting,' suggesting store-level aggregates. With no output schema, this ambiguity is critical. The description also does not explain what a returned change row looks like, making it incomplete for an agent to confidently invoke the 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 detailed descriptions for all three parameters. The main description does not add parameter-specific semantics beyond what the schema already provides; the baseline_key description in the schema gives extra context about scoping, so the baseline 3 is appropriate.

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 clearly states it watches a Shopify store's catalogue and returns only products whose price or availability changed since the previous check. This distinguishes it from siblings like shopify-store-intelligence (general intelligence) and tech-stack-change-detector (tech stack focus). The baseline creation behavior is also noted.

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 description implies use for monitoring price/availability changes over time ('since the previous check', 'first run creates baseline'), but it does not explicitly state when to prefer this over alternatives or provide exclusion criteria. The parameter description adds context about scheduled runs, but the main text lacks direct comparison to sibling tools.

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