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

The annotations already declare readOnlyHint and openWorldHint, so the description's safety burden is low. It adds meaningful behavioral details: findings are sorted by importance, output includes a fix action, and the tool explicitly excludes performance scores. This goes beyond the annotations without contradicting them.

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 concise yet information-dense: it starts with the core purpose, then clarifies non-overlap with a sibling, gives concrete examples, and ends with usage guidance. Every sentence earns its place, and the structure is logical and front-loaded.

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 a rich input schema, annotations, and an output schema, the description covers all necessary context: what the tool returns, what it does not return, how results are ordered, and how to present them. It fully equips an agent to decide when to invoke the tool and what to do with the results.

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 has 100% coverage with clear descriptions for both `path` and `project`. The description does not add parameter-specific details, but it does mention 'each with an address' which relates to the path concept. Given the schema's completeness, the baseline 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 states the tool provides specific page problems, each with an address and an actionable fix. It explicitly contrasts itself with check_performance ('This is NOT a score') and lists concrete examples, making its purpose unmistakable and differentiating it from 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 explicitly name-drops check_performance and distinguishes when to use each ('the score is given by check_performance, and there is nothing to fix based on it'). It also gives presentation guidance ('Don't dump them as a list—name two or three main ones and ask'), which is actionable usage direction.

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