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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly mentions pagination, notes that missing provider measurements remain null, and clarifies that sessions are not people and conversion rates are per session. These are meaningful behavioral nuances beyond a simple 'get'. It does not state read-only status, but the verb 'get' implies it, and no side effects are suggested.

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, dense sentence that front-loads the primary purpose and then lists the detailed components, followed by two clarifying caveats. It is efficient and avoids redundancy, though it packs many terms into one sentence that could be slightly restructured for easier scanning. It earns a 4 for being concise and well-ordered.

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?

Given the absence of an output schema, the description enumerates the key returned data elements (landing pages, engagement, page value, overview, engines breakdown, etc.), which is critical for an agent to understand what it will receive. It also explains metric interpretation and null behavior. It does not cover error handling or rate limits, but for a read-only get tool with pagination, these are minor gaps. Overall, it provides sufficient context for correct invocation.

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%, so each parameter (cursor, pageSize, windowDays) already has a clear description in the schema. The tool description adds minimal parameter-related detail, only referencing 'fixed window' and 'paginated', which are already implied by the schema. Per the rubric, a baseline of 3 is appropriate when the schema fully documents parameters.

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 uses a specific verb ('Get') and resource ('AI-referral landing pages') and enumerates the full set of returned data components (engagement, page value, overview, engines breakdown, provider provenance, coverage gaps, native metrics). This clearly distinguishes it from sibling tools like devtune_get_adoption_metrics or devtune_get_traffic_summary, which focus on different data domains.

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 provides clear context about what the tool returns but does not explicitly state when to use this tool over alternatives. There are no exclusion criteria or alternative tool names mentioned. However, the detailed scope ('AI-referral') implies its use case, and the caveat about sessions vs. people clarifies interpretation. It stops short of guiding tool selection.

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