cxa_scan_performance

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

With no annotations, the description carries the full burden and does well: it discloses the execution model (real Chromium browser run entirely by this MCP server, no external API), the breadth of the scan (6 browser/device profiles), and the return format (Markdown dashboard with grades and recommendations). It omits scan duration, concurrency/rate behavior, and any auth or reachability requirements, which are the remaining behavioral gaps.

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 definition is front-loaded with the core action and then layers in measurement list, execution model, output shape, and scope in a logical order. The long metric enumeration and profile list are dense but each clause adds decision-relevant information; the only slight cost is length without a hard need for every listed metric.

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?

No output schema exists, so the description appropriately explains the return value (rich Markdown dashboard with load bars, A+–F grades, mobile vs desktop comparison, recommendations). Combined with the stated scope exclusions and execution model, an agent has enough to invoke and interpret the tool; the unmentioned 'region' parameter and absence of timing/rate expectations are minor residual gaps.

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 description coverage is 100%, so both parameters are fully documented in the schema, and the baseline is 3. The description references 'the given URL' but adds no syntax, validation, or format detail beyond the schema, and the optional 'region' metadata parameter is not mentioned at all, so there is no meaningful semantic lift.

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 ('Performs a CX Assurance performance scan for the given URL') and then enumerates exactly what it measures (TTFB, FCP, DOM Content Loaded, transfer size, 6 device profiles). The closing scope sentence ('Performance metrics only – no accessibility, SEO, or security data') sharply bounds the tool, so an agent knows precisely what it does and does not do.

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?

Gives clear context for when the tool applies: it runs a real browser scan server-side with no external API dependency, and it explicitly excludes accessibility, SEO, and security data, which routes the agent away from misusing it for those audits. No siblings exist to compare against, and it does not state prerequisites (e.g. whether the target must be publicly reachable), so it stops short of full when/when-not guidance.

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