Full report

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

Beyond the sparse annotations (openWorldHint true, readOnlyHint false), the description discloses critical behavioral traits: it is 'SLOW, several minutes', it saves files when directory is passed, 'The folder must already exist; nothing is created and nothing is overwritten', and it differentiates between file-based HTML (embedded fonts, ~150KB) and conversation HTML (smaller). This is rich, non-contradictory context that greatly exceeds what annotations provide.

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 long but front-loaded with purpose and return types, followed by imperative usage instructions. Each sentence provides necessary operational detail, though some redundancy exists (e.g., asking the user for a folder is emphasized multiple times). The structure is organized and effective, not bloated, so a 4 is appropriate.

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?

Given the tool's complexity—5 parameters, file output, HTML generation, speed, and user interaction requirements—the description covers all critical aspects: outputs, side effects, prerequisites, performance, and file/HTML behaviors. There is no output schema, so the explanation of return values ('readable report, HTML, and JSON') is sufficient. This is a complete and thorough description.

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?

Schema coverage is 100%, so the baseline is 3. The description adds substantial meaning for 'directory' (must exist, user-named, not invented, can fall back to server folder) and 'html' (include or exclude based on user's need), which goes beyond the schema definitions. It does not add much for 'runs' or 'urls', but the added context for these key parameters justifies a 4.

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 states the tool's function with a specific verb and resource: 'The whole picture for a page in one call: scores with their spread, real-user data if Google has any, and what is failing ranked by what fixing it is worth.' It clearly lists the three outputs (readable report, HTML, JSON) and distinguishes itself from siblings like check_pagespeed or diagnose by framing itself as the comprehensive aggregate report.

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 gives clear operational context, including when to use the HTML ('USE THE HTML by saving it to a file the user can open or forward'), when to set 'html false', and explicitly instructs to 'ASK THE USER WHERE THEY WANT IT FIRST' before calling. It also mentions cost comparison to check_pagespeed. However, it does not explicitly state when not to use this tool or name alternative tools for specific scenarios, so it is not a perfect 5.

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