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

Beyond readOnlyHint=false and openWorldHint=true, the description discloses the main cost driver (per-page duration, slower with build=true) and the side effect of writing artifacts to an output location with returned paths and similarity scores. It does not say whether existing output directories are overwritten or what happens on partial failure, so it stops short of full transparency.

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?

Two tightly packed sentences, front-loaded with what is cloned and generated, followed by timing and return values. Nearly every clause earns its place; the desktop/mobile width detail is the only bit that leans toward implementation trivia.

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 nine parameters and no output schema, the description carries the return-value burden and does so ('Returns output paths and scores (percent identical)'). Combined with the full schema coverage and cost disclosure, an agent has enough to invoke it correctly; failure modes and overwrite behavior are the remaining 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 every parameter is already documented, which sets the baseline at 3. The description adds modest context by tying throughput to page count and clarifying the desktop/mobile scoring widths, but contributes no new semantics for parameters like remove, waitMs, styling, or frameworks.

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 concrete verb and resource ('Clone a website's frontend') and enumerates exactly what is captured (markup, CSS, fonts, images, scroll animations) and what is produced (static preview plus Next.js and Astro projects). It does not differentiate from siblings like verify_clone, and in fact overlaps with them by also scoring the clone, which slightly muddies which tool to pick.

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?

No explicit when-to-use or when-not-to-use guidance, and no mention of when to prefer verify_clone or read_report. The time estimate ('~1 minute per page (several minutes with build=true)') implies when the expensive path is worth it, but the agent must infer routing between siblings.

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

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

readOnlyHint=true already establishes the safety profile, and the description adds real value by enumerating the returned payload (manifest, per-width scores, diff image paths, worst regions) — important because there is no output schema. However, it says nothing about failure behavior when outDir is missing or contains no report, so it only partly compensates.

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 dense sentence with no filler, and the most useful content (the return payload) is front-loaded. It is a grammatical fragment with no verb, which slightly weakens its standalone readability.

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 single-parameter read tool with readOnlyHint and no output schema, the description covers what comes back, which is the main gap it needed to fill. It omits error/empty-report behavior and any hint that 'latest scores' may reflect a prior verify_clone run, leaving some agent-relevant context 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 parameter with 100% schema description coverage ('Output directory of a previous clone'), so the baseline is 3. The description does not reference outDir or clarify path format/relative-vs-absolute semantics beyond what the schema states.

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 names the resource (a clone's report) and enumerates its contents — pages, targets, per-width scores, diff image paths, worst regions — which is specific enough to separate it from clone_website and verify_clone, which perform actions rather than read a stored artifact. It stops short of an explicit verb ('returns/reads'), framing the purpose as a content list rather than an action.

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?

There is no statement of when to call this versus clone_website or verify_clone, and no prerequisite that a prior clone must exist (that constraint lives only in the outDir schema description). An agent must infer the usage context entirely from the tool name and sibling list.

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

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

Annotations declare readOnlyHint=false and openWorldHint=true, and the description is consistent: 'build and score' signals a real build that writes output and hits the site. It also adds interpretive value by stating 'A score drop means the refactor changed rendering.' It omits practical traits such as cost/time or where results are stored.

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?

Three short sentences, front-loaded with the core action before the target guidance and the interpretation note. Slightly dense quoting of enum values ('["next"]' / '["astro"]') duplicates schema detail rather than earning its space.

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 still covers purpose, use case, target meaning, and how to read results. The remaining gap is whether the run produces an artifact consumable by read_report, which an agent would want to know given that sibling.

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, but the description genuinely clarifies the vague 'targets' field by explaining that 'next'/'astro' build and score a generated project versus the default preview scoring. It says nothing about outDir or widths beyond the schema, so it is a modest but real addition.

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 ('Re-score an existing clone against the original site'), which cleanly separates it from the sibling that creates clones and the one that reads reports. The parenthetical use case ('after refactoring the generated components') further pins down intent.

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 a concrete trigger for using it ('after refactoring the generated components') and explains the targets choice for building a generated project. It does not explicitly name when not to use it or point at a sibling alternative, so it stops short of a 5.

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