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

With no annotations, the description carries the disclosure burden. 'Measured anatomy' implies a read-only analysis, and the sample-size/cap details add useful context, but there is no explicit statement of side effects, output representation, freshness, or other runtime behavior.

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 compact sentence front-loads the artifact and uses a colon to enumerate the exact metrics. Every phrase earns its place; there is no filler or boilerplate.

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 no-parameter tool, the description supplies enough context to invoke it: what the analysis covers, the sample size, and the key comparison condition. It does not describe the response shape, but with no output schema this is a minor gap.

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 tool has zero parameters and an empty input schema, so there is nothing the description needs to explain. The baseline of 4 applies because no parameter guidance is required.

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 identifies a concrete artifact—a measured anatomy of 160 Claude Code sessions—and names the metrics covered: cache-read share, oversized tool-output share, and the replay effect. It is specific enough to distinguish this from sibling tools, though it lacks an explicit verb like 'returns' or 'shows' to state the operation.

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?

There is no guidance on when to choose this tool over its siblings, even though tools like show_hn_claude_code_stats and issue_gap_map are plausibly related. The content implies a use case around Claude Code cost analysis, but the description never states when it should or should not be used.

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