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

Annotations already cover the safe, read-only, idempotent nature of the tool, so the description's burden is lower. It adds useful behavioral context by stating that it returns per-site breakdowns plus shared traits, which goes beyond the simple 'compare' framing and clarifies the output style without overpromising.

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 dense sentence that front-loads the core action and scope, then immediately states what the agent will get back. No filler, no repetition of schema fields, and the house-style purpose is included without bloat.

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 one parameter, full schema coverage, and safety annotations, the description is nearly complete. Since there is no output schema, it appropriately summarizes the return shape ('per-site breakdowns plus what they share'), which is enough for an agent to invoke the tool and calibrate expectations, though a bit more structure would elevate it further.

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?

The single parameter `slugs` has 100% schema description coverage, including examples and range constraints, so the description does not need to add much. It adds context about what the slugs represent ('captured sites') and what comparison dimensions are used, but that is tool-level context rather than deeper parameter 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 uses a specific verb ('Compare'), names the exact resource ('2-4 captured sites'), and lists the comparison dimensions (palette, typefaces, macrostructure, scales, etc.). It also distinguishes itself from sibling tools by framing the output as a house-style triangulation across references, which is unique among the listed siblings.

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 clearly communicates when to use the tool: when you have 2-4 captured sites and want to triangulate a house style. It does not explicitly name alternatives or exclusions, but the context is unambiguous and leaves little inference for an agent deciding whether to call this tool.

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