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

Annotations already declare readOnlyHint and destructiveHint, so the description adds value with 'Read-only, free' and, more importantly, a detailed explanation of the like_for_like field's true/false/null semantics and the warning not to report deltas unless true. This is meaningful behavioral context beyond the annotations.

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 contains useful details but is somewhat verbose and redundant: the opening rhetorical question is not essential, and the ALWAYS/Never sentences overlap. The phrasing 'The proof read for a period' is also awkward. Still, it front-loads the core purpose and keeps the critical caveat.

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 does a good job of listing the scoreboard's key components and thoroughly explains the like_for_like flag's interpretation. It lacks a formal return-structure description but covers the most important fields and semantics for a read-only summary 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?

The input schema already provides 100% coverage for the single parameter, including default and clamping behavior. The description adds no additional parameter semantics, so the baseline score of 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 identifies the tool as a period scoreboard covering AI visibility at start/end, moves shipped, scans, and receipts, which distinguishes it from narrower siblings like get_visibility or get_outcomes. However, the awkward phrasing 'The proof read for a period' obscures the otherwise clear purpose.

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 opening question 'Did the growth work move anything?' sets a clear use case, and the explicit instruction to always check like_for_like before reporting a change provides actionable guidance. It does not explicitly name alternative tools or say when not to use this tool, so it stops short of a 5.

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