Profile a page (Query Monitor style)

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

Substantial disclosure beyond the readOnlyHint/destructiveHint annotations: the single-use token mechanism that leaves ordinary visitors unaffected, the anonymous-by-default behavior, the hooks-excluded-by-default performance tradeoff, the credential-free as_logged_in switch, and the companion-plugin prerequisite. Nothing contradicts the annotations.

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?

Four sentences, each earning its place: collection scope, the instrumentation mechanism, the auth default, and the plugin dependency. The enumeration of collected data is long but densely informative rather than padded, and the core purpose is front-loaded.

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 complex instrumenting tool with no output schema, the description covers the non-obvious invocation facts: plugin requirement, single-use token, anonymous default, sections default, and the credential-free logged-in mode. Minor gaps: no failure behavior if the plugin is absent and no note on overall request-time impact.

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 the baseline of 3 applies. The description does not need to explain parameters; the schema already documents url defaults, site_id resolution via list_sites, the sections enum, as_logged_in behavior, and the slow_query_ms threshold.

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 — 'Profile how WordPress builds one front-end URL' — and enumerates exactly what is collected: template, database queries, assets, outbound HTTP, warnings, conditionals, memory and findings. The Query Monitor analogy plus the 'one URL' scope clearly distinguishes it from siblings like get_page_html, get_template_for_url, or get_preview_url.

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?

Provides clear context: it is a diagnostic profiler gated by a companion plugin, instruments only one request via a single-use token, and defaults to anonymous visiting. It does not explicitly name sibling alternatives or state when not to use it, so a point is lost for missing exclusions.

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