Diagnose a page

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

Beyond the readOnlyHint and openWorldHint annotations, the description reveals significant behavioral details: it only reports failures consistent across ALL analyses, provides median and spread for savings, explains the weighted ranking logic, and explicitly warns that savings do not add up. This goes far beyond the annotations in explaining the tool's actual 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?

Although the description is longer than average, every sentence adds critical information: purpose, consensus filtering, variance reporting, ranking logic, overlap of savings, and performance impact. It is front-loaded with the main purpose and remains tightly structured.

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 tool with only two parameters and no output schema, the description covers all essential context: what it reports, how failures are determined, how to interpret savings, and the tool's speed/cost characteristics. This is complete enough for an agent to invoke and interpret results correctly.

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?

With 100% schema coverage, the schema already documents both 'runs' and 'urls'. The description reinforces the meaning of 'runs' by referring to 'distinct analyses,' but adds no new parameter-level detail. The baseline of 3 applies because the schema carries the descriptive burden.

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 opens with 'Report what is FAILING on a page and rank it by what fixing it is worth,' which precisely states the tool's verb, resource, and output. It clearly distinguishes itself from siblings like check_pagespeed by focusing on failure diagnosis rather than overall speed.

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 provides operational context by stating 'SLOW, like check_pagespeed, and costs no extra API calls,' which helps agents decide when it is appropriate to use. It doesn't explicitly name alternatives or exclusions, but the performance context is clear enough for informed use.

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