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

Annotations already declare readOnlyHint/openWorldHint/non-destructive, and the description still adds substantial behavioral context: it counts every img element rather than sampling, reports how many were read and how many skipped as aria-hidden or presentational, warns when the page was truncated, and lists what it structurally cannot see. It even states its own judgment limit ('cannot judge whether a clean description is accurate'), which is unusually candid.

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?

Front-loaded with the core action and the input options before the long enumeration of checks, and every clause adds a distinct detectable pattern rather than filler. The middle section is a dense run-on list of checks, which is information-rich but harder to parse than it needs to be.

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 carries the burden of describing results and does so: counts read/skipped, per-issue flags, meta-tag coverage, and truncation notice. Combined with explicit coverage limits, an agent has everything needed to call it and interpret the response.

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 both parameters are already documented, and the description only restates the url-or-html choice plus the 'public' constraint on the URL. It adds nothing on precedence (what happens if both are supplied) or on the html payload expectations beyond what the schema says, so 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 ('Reads alt text on a page') and enumerates exactly what it inspects and flags, so the agent knows this is an alt-text-specific audit rather than a general accessibility crawl. It never names siblings such as audit_page_accessibility, so differentiation is inferred from scope alone rather than stated.

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 tells how to invoke it ('Pass a public url or html') and discloses a boundary ('Reads delivered markup only: script-added images, CSS backgrounds and inline SVG are not seen'), which implicitly steers the agent to another tool for rendered-DOM cases. However, it gives no explicit when-to-use/when-not and never points to a specific alternative.

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