ready→made MCP

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

With no annotations, the description carries the burden well: it discloses the deterministic engine, the return shape ('paste-ready payload plus a short instruction'), the section-at-a-time layer limit, and the plan requirement. Missing only error/failure behavior and any rate limits.

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 purpose, then targets, then operational constraints — the ordering matches how an agent needs the information. It is dense but nearly every clause carries signal; the parenthetical '(same frame → same output, no LLM guessing)' is slightly promotional yet justifies the determinism claim.

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 6-parameter tool with nested options and no output schema, the description covers purpose, targets, limits, plan gating, and return format. The main remaining gap is error/edge-case behavior (invalid node, layer-limit exceeded, expired hosted assets), but nothing essential for a correct first call is missing.

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 baseline is 3, but the description adds real meaning beyond the schema by elaborating each target format (container JSON for Elementor paste, core block markup, self-contained HTML, Oxygen Classic vs 6). The nested `options` fields are left entirely to the schema, which is acceptable given full coverage.

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 ('Convert ONE Figma frame into a native WordPress builder layout'), names the engine and its deterministic property, and enumerates all six output targets. The 'ONE frame' emphasis and target list make it unmistakable against siblings like inspect_figma or list_targets.

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 concrete when-to guidance ('Convert sections one at a time (hero, features, footer…)'), an explicit failure condition ('A whole page in one call hits the layer limit'), and a prerequisite ('Requires a ready→made Pro or Lifetime plan'). It does not name a sibling tool or say when to prefer inspect_figma first, so it falls short of full alternative routing.

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?

With no annotations, the description carries the full burden, and it does disclose the salient behavior: this is a non-converting inspection that previews the convert limit, and it is 'Free' (no credit consumption). It does not explicitly declare read-only/non-destructive status or how large the response can get; caching and token handling are covered only by the schema, not the prose.

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 sentences with the verb and the non-conversion constraint front-loaded, followed by the concrete output inventory. The enumeration is long but every item is decision-relevant for choosing a frame; slightly denser than strictly necessary.

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?

There is no output schema, so the description must explain the return value — and it does so item by item, including the convert-limit verdict and candidate frames that drive follow-up calls. Nothing an agent needs in order to call this correctly and interpret the result is missing.

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 all five parameters (url, node, depth, refresh, figmaToken) are already fully documented in the schema. The description adds no syntax or format meaning beyond hinting at the layer-tree depth and frame selection. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Outline') and resource ('a Figma file or frame'), then enumerates exactly what comes back: layer tree, node count, text/image/vector counts, convert-limit status, and candidate child frames. The explicit 'WITHOUT converting' clause plus the named sibling convert_figma makes it distinguishable from its alternatives at a glance.

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 two concrete triggering conditions — the user supplies a whole-file link, or convert_figma reports a frame is too large — and implies the alternative (convert_figma) that should be used instead once the right frame is found. No inference required to decide when to call this.

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?

With no annotations supplied, the description carries the full burden and does disclose the key traits: the operation is free of charge and returns a one-line paste/import note per format. It does not explicitly state read-only/no-side-effect behavior or auth requirements, but "List" plus "Free" makes the cost and safety profile clear.

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 sentences, both earning their place: the first names what is returned and the format of each entry, the second states cost and the decision it resolves. The parenthetical enumeration is front-loaded rather than buried.

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 zero-parameter, non-mutating lookup with no output schema, the description covers everything needed: what comes back, in what shape (one-line note per format), that it costs nothing, and when to reach for it. Nothing required to invoke it correctly is missing.

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?

The tool takes zero parameters, so there is nothing to disambiguate. The description still adds value by explaining the output feeds the `target` argument of other tools, connecting this no-arg call to a parameter elsewhere.

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 (List) and resource (WordPress builder formats the service can emit), and enumerates the actual values returned: Elementor, Gutenberg, Oxygen 6, Oxygen Classic, Etch, plain HTML. An agent can immediately tell this apart from the Figma-oriented siblings convert_figma and inspect_figma.

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?

"Free; call it when unsure which `target` to use" gives an explicit trigger condition tied to a concrete downstream decision. It stops short of naming when-not-to-call (e.g., skip it if you already know the target), but the context is clear enough to act on.

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