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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds the behavioral detail that results are ranked by occurrence count and refer to interaction contexts (chat, search, navigation, form submission). This is useful but modest; it does not go into response format or filtering behavior, though an output schema exists.

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 compact and immediately front-loads the core meaning. Each sentence adds value: what is returned, how it differs from a sibling, and when to use it. There is no redundant phrasing or filler.

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?

For a simple, read-only analytics tool with two optional, fully documented parameters and an output schema, the description covers the essential context. It explains the data semantics, ranking, and the key distinction from the most similar sibling, making the tool complete enough for correct selection and 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?

Input schema coverage is 100% for both optional parameters, including defaults, allowed enum values, and the custom date-range pattern. The description adds no parameter-specific information, which is acceptable because the schema already fully documents limit and time_filter.

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-resource pair, 'get top interaction sources,' and states the exact meaning: page URLs the user was on when interacting with the embed, ranked by occurrence count. It also explicitly distinguishes this from get_top_clicked_urls, making the tool's identity unambiguous.

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 names a direct sibling, get_top_clicked_urls, and clarifies the key differentiator: origin page versus destination. It also states a clear use case, finding which host-site pages drive embed engagement. It lacks an explicit 'when not to use' instruction, but the contrast with get_top_clicked_urls effectively covers the main alternative.

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