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

Annotations already declare readOnlyHint/idempotentHint and non-destructive, so safety is covered. The description adds real value beyond them by disclosing the merge behavior ('pass only the settings to change and everything else in the link is kept') and, since there is no output schema, what the call returns and how the two URLs differ (studio vs bare canvas for iframes).

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 tight sentences, front-loaded with the purpose and followed by the mode selection and return values. Dense but nearly every clause carries information; no filler or repetition of structured fields.

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 correctly fills the return-value gap (share_url vs embed_url) and covers the two invocation modes for an 8-parameter tool with a nested config object. Remaining details (ignored-key handling, v3 color behavior) live in the schema, so the description is sufficiently complete.

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 75% (only 'shape' and 'density' are undocumented) and the config parameter is richly annotated. The description still adds meaning beyond the schema by explaining the relationship between 'look' and 'share_url' and the partial-update/merge semantics of passing only changed settings.

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?

Names a specific verb and resource (build Globestudio URLs / share links) and immediately scopes the two operating modes: start from a preset via 'look' or modify an existing link via 'share_url'. This implicitly distinguishes it from the read-oriented sibling read_share_url, so an agent can tell what this tool does without opening the schema.

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 routing for the two entry paths ('Start from a preset (look) or change an existing link (share_url, e.g. one the user pasted)') plus the key usage rule that only changed settings need to be passed. It lacks explicit when-not guidance or named alternatives (read_share_url, preview_url), 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.

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is fully covered. The description adds some value by revealing the shape of the return (paste-ready code in three flavors), which matters given there is no output schema, but it says nothing about auth, limits, or whether the code embeds live content.

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, zero filler, and the core action is front-loaded before the framework options. Every clause carries information the agent needs to pick a framework value.

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 correctly compensates by describing what comes back (paste-ready embed code). The required 'look' parameter is only covered as "Preset id." in the schema, but sibling find_presets/list_presets reasonably supply preset discovery, so the gap is modest.

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 75%, so the baseline is 3, but the description maps each enum member to a concrete target (iframe → HTML for Webflow/Notion/WordPress, react → drop-in component, script-tag → vanilla JS loader), which is meaning beyond the bare enum. The width/height parameters are left entirely to the schema.

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+resource ("generate ... embed code") and the scope ("for any preset"), so an agent can tell it produces embed snippets rather than URLs. It does not, however, distinguish itself from siblings like build_share_url or preview_url, which also emit user-facing artifacts.

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 gives selection guidance for the framework parameter (iframe for Webflow/Notion/WordPress, react for a drop-in component), which is genuinely useful routing info. But it never says when to use this tool versus build_share_url, preview_url, or read_share_url — usage is only implied.

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 already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add behavior beyond that. It does: matching is fuzzy rather than exact, and results come back "ranked matches," which tells the agent to expect approximate, ordered output. Limits (result cap, match threshold) are still undisclosed.

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 verb and resource, then four compact examples on one line, then the return behavior. No sentence is padding; the examples earn their space by showing input semantics that the schema does not.

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 one-parameter search tool with full schema coverage and no output schema, the description supplies input semantics and return behavior ("ranked matches"), which is nearly everything needed. It stops short of describing result shape or how matches feed into sibling tools like preview_url or build_share_url.

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% and the single parameter is documented as "Single word or short phrase," so baseline is 3. The description goes further by demonstrating the semantic space of acceptable keywords (style, aesthetic, use-case) with concrete mappings, which tells the agent what kinds of tokens actually match.

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 mechanism ("Fuzzy-find presets by vibe / aesthetic / use-case keyword") against a clearly named resource. The keyword-driven fuzzy match inherently separates it from the sibling list_presets, which would enumerate rather than search. An agent can select it without opening the schema.

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?

Usage is implied by the worked examples ('synthwave' → Vapor), which show the intended input style, but there is no explicit when-to-use statement, no exclusion, and no mention of list_presets as the alternative for full enumeration. Adequate but leaves routing to inference.

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 already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered structurally. The description adds behavior the annotations do not: it returns EVERY preset unfiltered, implying no input-driven narrowing, and it enumerates the response fields, which is valuable given there is no output schema.

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, no filler, and the action plus returned payload is front-loaded before the routing hint. Every clause earns its place.

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 compensates well by listing the return fields, and the annotations cover safety. The only real gap is that the boundary with find_presets is never stated, which matters since both could appear to answer 'show me looks'.

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 the baseline is 4 and there is no parameter semantics to document. Nothing in the description misrepresents the parameterless contract.

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 (Globestudio look presets) and enumerates exactly which fields come back (id, name, blurb, vibe tags, thumbnail URL, embed URL). The word 'every' plus the field list distinguishes it from the narrower find_presets sibling.

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?

'Call this first when the user asks about available looks' gives an explicit trigger condition, which is strong usage guidance. It stops short of naming find_presets as the alternative for filtered/searched lookups, so the when-not case is left to inference.

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 already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds value by disclosing what is returned (two URLs: canonical live embed URL and thumbnail PNG URL), which matters since there is no output schema.

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 short sentences, zero filler, with the concrete deliverable (embed URL + thumbnail PNG) front-loaded before the use case.

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 trivial single-param read tool with full annotation coverage, the description supplies purpose, return values and a selection rationale. Nothing an agent needs 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?

Schema description coverage is 100% with one required param ('look' = 'Preset id.'). The description only restates this as 'a single preset', adding no syntax or format detail beyond the schema, so the 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 (get the embed URL + thumbnail PNG URL for a preset) and scopes it to a single look. It implicitly separates itself from build_share_url by noting it avoids building a full share URL, though it never names the sibling tool directly.

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?

"Useful when you want to render an inline preview without building a full share URL" gives a clear condition for choosing this over the share-URL path. There is no explicit when-not guidance or named alternative, but the use context is unambiguous.

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 already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds that the operation is a decode that extracts look and settings, but says nothing about failure behavior for malformed or expired links, which matters for a link-parsing tool. Adequate but not rich beyond 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?

Two sentences, front-loaded with the action and scope, followed by the routing instruction. No filler or restated field names.

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 one simple parameter, no output schema and full annotation coverage, the definition covers purpose, input shape and workflow. The only gap is that it does not describe the shape of the decoded result or error cases, which is a minor omission for a single-param read tool.

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% and the single parameter is well documented, so the baseline would be 3. The description goes further by enumerating the accepted link formats, which the schema example ('https://globestudio.app/?c=…') does not convey, so it adds real meaning about valid inputs.

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 gives a specific verb (decode) and resource (a Globestudio share link), and enumerates the three link shapes it accepts (studio share link, /looks/<id>, /embed URL). It also states what it yields — 'the look and settings it carries' — which separates it from the write-oriented sibling build_share_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?

It states the triggering condition explicitly ('Use it when the user pastes a link') and names the downstream alternative, build_share_url, along with what to do with the result. An agent knows both when to pick this tool and what to do next without opening another schema.

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