Agent-readiness audit

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds what the agent otherwise could not know: it returns per-criterion scores, findings and fixes. It leaves out whether the page must be fully loaded or how long the audit takes, which keeps it from a 5.

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 front-loaded sentence with the purpose first and the criteria list second; every clause carries information. The criteria enumeration is long but necessary to distinguish the tool from its siblings.

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 must convey the return shape, and it does ('per-criterion scores, findings and fixes'). For a zero-required-parameter read-only audit that is close to sufficient; only environmental prerequisites are unstated.

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?

There is a single optional parameter with 100% schema description coverage, which already explains tabId and its default to the session target tab. The description adds nothing beyond that, so the baseline 3 applies.

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?

States a specific verb and resource ('Scores how ready the page is for AI agents') and enumerates the exact criteria covered (accessibility tree, CLS, WebMCP tools, llms.txt), which separates it from general-purpose siblings like perf_metrics or devtools_issues. It does not name an alternative explicitly, but the scope is unambiguous.

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?

Usage is only implied: an agent can infer it should run this to assess a page's agent-friendliness, but there is no statement of when to prefer it over perf_metrics or page_snapshot, no preconditions (page loaded, network available), and no exclusions.

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