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

Annotations already declare readOnlyHint=true and openWorldHint=false, and nothing in the description contradicts that — it frames the tool as generating a brief, not mutating state. The description goes well beyond annotations by disclosing the actual deliverable contents: specs, hook formulas, per-tool image prompt sizes, beat sheet, and a compliance checklist. It could still say whether the brief is returned inline only or persisted.

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?

A single front-loaded sentence with the verb and scope first, followed by the output enumeration. The list is long but each item conveys distinct deliverable value rather than repeating the schema, so it earns most of its length; a bulleted or clause-split structure would read slightly better.

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 carries the burden of explaining what comes back, and it does that thoroughly. The 3 required parameters are self-evident from the schema; the gap is guidance on which of the 11 optional parameters actually change the brief's content, which the description leaves 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?

Schema description coverage is 43%, below the 50% threshold, so the description is expected to compensate for the 14 parameters. It only indirectly maps to inputs — compliance checklist implies sponsored/giveaway/aiGenerated, per-tool sizing implies platform/format, beat sheet implies videoSeconds — but it never states these explicitly, leaving tone, offer, phase, eventId, product and niche unexplained outside 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?

Specific verb ('Create a production brief') plus a precisely scoped resource ('for one post, image, carousel, story, video or email'), with an enumeration of what the brief contains. It is clear what the tool produces, but it never names or contrasts sibling tools such as content_plan or platform_specs, so differentiation is left to inference.

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 phrase 'for one post, image, carousel, story, video or email' implicitly scopes this to a single asset, which hints at a plan-vs-asset split with content_plan. However, there is no explicit when-to-use, when-not-to-use, or prerequisite statement, and no alternatives are named.

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?

The description is rich in behavioral details beyond annotations, such as specifying that 'signup' emails a key, 'status' returns limits, and 'upgrade' returns a 'secure Flutterwave checkout link.' This defines the outcome of the function calls.

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 description is highly structured, progressing logically from tool identification to individual action details and ending with behavioral constraints, ensuring every word adds 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?

Despite lacking an output schema, the description is complete for a complex tool. It specifies the result type for every relevant action (API key, plan details, or checkout link), allowing the agent to anticipate outcomes.

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?

Given that schema coverage is 0%, the description is crucial. It explicitly defines the function of the 'action' enum values (signup, status, upgrade) and specifies the associated parameters (e.g., 'signup' requires an email).

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 tool clearly identifies itself as the 'Cloud account' manager. Although its purpose is well-defined, it does not explicitly compare its scope to the many content-focused siblings (e.g., page_stats or start_campaign), which would have achieved a 5.

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 provides explicit conditional usage instructions for 'upgrade' (returning a link, not taking payment) and a vital security constraint ('Never ask for card details in chat'). This is exceptionally helpful for guiding agent behavior.

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 this is a non-readonly, open-world, non-destructive operation, and the description adds real value on top: it returns exactly one DNS record, HTTPS is provisioned automatically, and the check flag polls liveness. It does not say what happens on verification failure, whether repeated calls without check create duplicates, or whether the Pro gate causes an error — modest gaps for a mutation tool.

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 outcome, then the return value, then the follow-up call pattern. Every clause carries information: the 'Pro' tier flag, the HTTPS behavior, the single DNS record, and the liveness check.

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 3-parameter, no-output-schema tool, the description covers purpose, return value (one DNS record), and the second-call verification flow. It is close to complete; only error and idempotency behavior on repeat calls is unaddressed.

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 only 33%: 'site' is documented in the schema, 'check' is explained only in the description, and 'hostname' has no textual description in either place beyond a minLength constraint and the 'sale.korakicks.com' example. The description partly compensates by illustrating hostname format and check semantics, but multi-site selection ('site') is 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?

The description names a specific outcome (serving published pages on the user's own domain with automatic HTTPS) and gives a concrete example hostname, so the agent knows exactly what the tool accomplishes. It does not reference any sibling tool (e.g. publish_page) to differentiate, but the purpose itself is unambiguous.

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 second call pattern is spelled out explicitly: 'Call again with check: true to see if it is live,' which is genuine when-to-use guidance for the two-phase workflow. It also implicitly scopes this to published pages and a paid tier ('Pro'). What is missing is any prerequisite or exclusion, such as domain ownership verification or what to do if the record never goes live.

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=true and openWorldHint=false, and the description adds substantial behavior beyond that: cadence caps on email and WhatsApp to avoid unsubscribes, campaign-phase assignment tied to the most important upcoming event, evergreen fallback on quiet days, and no-sales guidance on observances like Remembrance Day. These are real generation rules an agent could not infer from structured data.

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, front-loaded with what is generated, then the awareness dimensions, then phase logic, then the return. Dense but every sentence carries information; the parenthetical phase list is long but useful enumeration.

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 12-parameter tool with no output schema, the description covers the generation logic and explicitly describes what comes back (slots to fill with captions and assets). Defaults for startDate/endDate/postsPerWeek/format are left entirely to the schema, which is acceptable given 83% coverage but a small gap.

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 83%, so baseline is 3, but the description adds meaning: 'regions' drives event relevance ranking, 'platforms' interacts with cadence caps, and 'niche' shapes angles, hooks and shots. It does not clarify offer, format or postsPerWeek semantics beyond the schema, keeping it from a 5.

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?

Specific verb plus resource: 'Generate a day-by-day content calendar per platform for the coming weeks.' It is immediately distinguishable from siblings like event_calendar (event lookup) and asset_brief (asset creation) because it explicitly positions the output as slots to be filled later.

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?

Clear context: use it to plan posts across platforms, and the closing line 'Returns slots you then fill with captions and assets' routes the agent to a downstream tool. There are no explicit exclusions or named alternatives (e.g., when to prefer event_calendar first), 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 establish readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real value by disclosing the default window (next 90 days) and the shape of what comes back, including derived fields like 'days until' and hashtags. It does not mention rate limits or result-set size caps, which keeps it below a 5.

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 dense with information, and the core capability plus return contents lead before the usage nudge. No filler or redundant restatement of the name.

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 usefully describes what each result contains and states the default range, which is enough to call it correctly with zero required parameters. Minor gap: it never explains how minImpact or categories affect results, though the enums are self-evident.

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 71%, so most parameters are already documented in the schema (from/to/year/regions/includePast all have descriptions). The description reinforces the date-range and default behavior but adds nothing about minImpact or categories, leaving it at the baseline for this coverage level.

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 ('List holidays, shopping days, religious and cultural events') with scope ('any date range and region') and even enumerates the returned fields (dates, days until, promotion timing, content angles, hashtags). An agent knows exactly what this tool produces 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 explicit timing guidance ('Use this before planning any campaign'), which positions it ahead of siblings like content_plan and start_campaign. It stops short of naming those alternatives or stating when-not to use it, so it is clear context rather than full 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?

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the agent knows this produces output rather than reading state. The description adds the format-to-destination mapping (Sheets/Notion/Airtable, calendar apps), but never says whether the result is returned inline or written to disk, or what outputPath/local mode means behaviorally.

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, front-loaded with the verb and resource, then the formats, then the invocation hint. Nothing is redundant and no sentence could be dropped without losing information.

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 13-parameter, non-read-only tool with no output schema, the definition covers purpose and invocation but leaves the delivery mechanism (inline payload vs. file, role of outputPath) and most optional parameters unexplained. Adequate to call, not adequate to predict the result.

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 only 23% across 13 parameters, so the description must compensate. The format list maps cleanly onto the `as` enum and the 'same arguments as content_plan' line helpfully delegates semantics for the shared parameters, but the remaining nine parameters (offer, product, dates, postsPerWeek, focusEvents, outputPath) get no clarification.

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 (Export) and resource (a content plan from content_plan) plus the three output formats and their target integrations. An agent can distinguish it from the sibling content_plan, which generates rather than exports, though the description never says so explicitly.

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?

"Pass the same arguments you used for content_plan" is a concrete, non-obvious invocation instruction that tells the agent exactly how to prepare the call. It gives clear context but names no exclusions or when-not conditions (e.g., what to do if no plan exists yet).

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?

Adds substantial behavior beyond readOnlyHint/openWorldHint: conditional provider selection driven by environment keys, result contents (licence, author, attribution line), and a default filter that removes photos likely showing other brands' logos. These are non-obvious operational traits an agent could not infer from annotations or 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?

Four front-loaded sentences covering purpose, sourcing, result shape and usage advice; the sourcing/provider detail is dense but each sentence carries distinct information. Minor editorial advice is the only borderline filler.

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 usefully discloses result fields (licence, author, attribution), so return shape is covered. Pagination/count limits and orientation semantics remain unaddressed, a small gap for a 4-parameter 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 only 25%, so the description must compensate — and it partially does by implying allowBrands ("removed by default") and the intent of query (scene description). However, count and orientation are undocumented in both places, leaving the compensation incomplete.

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 ("Search commercially usable photos for pages and posts") and the licensing scope, which no sibling tool touches. An agent can immediately tell this is an image-sourcing tool rather than a publishing or planning tool.

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 usage context: stock photos for mood and backgrounds, while the product should be the seller's own photo. It also explains provider fallback conditions (PEXELS_API_KEY / UNSPLASH_ACCESS_KEY set). No explicit when-not or sibling alternative is named, but there is no competing sibling to route to.

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?

Adds real behavioral context beyond the annotations: copy is written only from given facts and never invents reviews, guarantees or prices; the countdown is honest; motion is scroll-linked not timed fades; mood photos are fetched from the network. With readOnlyHint=false and openWorldHint=true already declared, this is meaningful added context. It stops short of saying where the generated file lands or what the call returns (path vs URL).

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 the core promise, then organized into coherent blocks (art direction, media, holiday theme, output contents). Dense and mostly waste-free for a 35-parameter tool, though the niche-to-archetype catalog runs long and could be tightened.

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 35-param generator with no output schema, the description covers the deliverable well: a single HTML file with sticky mobile CTA, SEO/Open Graph tags, Product/Offer structured data and photo credits. The notable omission is the return contract — no statement of whether the call returns HTML, a path, or a hosted URL — which matters precisely because there is no output schema to fall back on.

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?

At 60% schema coverage across 35 parameters, the description does substantive work: it explains what images/productImage/videoUrl/modelUrl/autoImages do and how they interact, that archetype is an art-director override mapped to niche categories, and what layout "signature" changes. Still, roughly a third of parameters (outputPath, pageUrl, ctaText, discountPercent, features, faq, testimonials interplay) get no prose semantics, so it does not fully close the coverage gap.

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?

Opens with a specific verb+resource+artifact: "Generate a premium, ready-to-deploy sales page (one HTML file) built around what the user sells." That is unmistakable. It loses the top mark only because the closing line ("Deploy to Netlify Drop, Vercel, GitHub Pages...") sits near sibling publish_page and can read as if this tool deploys, without stating the boundary.

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 situational rules: works from minimal input (brand + product), no media means autoImages fetches free mood photos, holiday theme plus layout "signature" forces the art-directed holiday scene, variant re-rolls styling. These are conditional how-to-use cues rather than when-to-use-this-vs-sibling guidance, and no exclusion against publish_page is offered.

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=true and openWorldHint=true, so the safety profile is covered. The description adds real behavioral context — results are restricted to published pages, are broken down per product, and the inline example shows the shape of the returned data. It does not mention the look-back window behavior, plan-based retention, or pagination limits, so it stops short of rich disclosure.

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 concrete output content before the recommendation for use. The inline example ('Runner One: 48 WhatsApp clicks') earns its place by conveying output shape compactly.

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 read-only, single-optional-parameter tool with no output schema, the description conveys enough: what is measured, the scope of pages, the per-product breakdown and an output example. Only minor gaps remain, such as the time-window default and plan retention, which the schema already covers.

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 `days` parameter already documents its default of 30 and the 7-day free-plan cap, so the schema carries the parameter burden. The description adds nothing about the time window, which is acceptable at this coverage level but limits the score to baseline.

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 the specific metrics (views, WhatsApp order clicks, button clicks), the scope (published pages) and the granularity (per product), which is far more informative than the title 'Page results'. It does not name or differentiate against any sibling tool, though none of the listed siblings is a competing analytics tool, so the practical risk of confusion is low.

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 second sentence gives a concrete use case — tell the user what is selling and what to push next — which sets clear context for when an agent should reach for this tool. There are no exclusions or named alternatives, but there is no obvious competing tool to redirect to.

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=true and openWorldHint=false, so the safety profile is covered and the bar is lower. The description adds useful context about breadth of coverage (eleven platforms plus email), but says nothing about the shape of the response or whether it is a static bundled reference versus a live fetch.

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?

A single sentence with no filler, and the substance is front-loaded in the opening list of spec categories. The trailing platform enumeration is long but each item earns its place by defining coverage boundaries.

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-optional-parameter read-only lookup with no output schema, the description is close to sufficient: the enumeration effectively describes the returned content, and annotations cover safety. The only gaps are the return format and the behavior of the platforms filter, both minor for a static reference 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 description coverage is 100%, so the schema already carries the single optional parameter; the description adds nothing about the platforms filter, which accepts either a string or an array and defaults to all. Baseline 3 applies when the schema does the heavy lifting, and here the description contributes no extra parameter meaning.

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 enumerates exactly what the tool returns (image/video sizes, aspect ratios, length limits, caption limits, safe zones, cadence, tips) and for which platforms, so an agent can immediately tell this is a static reference lookup. It lacks an explicit verb, but the resource and scope are specific and no sibling covers this ground.

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 only implied by the content enumeration: an agent infers it should call this when it needs platform constraints. There is no explicit 'use when' statement, no mention of when not to call it, and no reference to any sibling such as content_plan or asset_brief that might also touch platform requirements.

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 cover the safety profile (not read-only, open-world, non-destructive); the description adds what the annotations cannot — that output becomes publicly reachable at a shareable URL, what the resulting address looks like, plan quotas enforced, badge injection on Free, and the authentication requirement with a self-service path to obtain the key.

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 tightly packed sentences with the core action and example URL front-loaded, followed by input modes and then constraints/auth. Dense but every clause carries information; the plan/badge sentence could arguably be trimmed but is load-bearing for expectations.

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 publishing mutation with no output schema, the description still discloses the return artifact (shareable link) and the shape of that link, plus quotas and auth. Minor gaps: behavior on republish to an existing path, and the 'title' parameter, are not addressed.

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 67% and the description fills key gaps: it explains html's origin ('from landing_page'), the file param's local-mode semantics, the nested 'page' object's purpose, and implies brand→subdomain and path→URL segment via the example link. Only 'title' remains unaddressed in both description and 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 and resource ('Put a sales page online and get a shareable link') and immediately clarifies the relationship with the sibling landing_page ('Pass the HTML from landing_page ... or "page" with landing_page arguments to build and publish in one step'). An agent can distinguish build-only from build-and-publish without opening schemas.

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?

Enumerates the three concrete invocation modes (raw html, local file path in local mode, nested 'page' object for one-step build+publish), states the plan-based differences (Free: 1 site/3 pages/badge; Pro: own domain, no badge), and names the prerequisite action (QUARTER4_API_KEY via cloud_account 'signup').

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=true and openWorldHint=false, and the description is consistent with a pure-analysis tool. It adds genuinely useful behavior beyond the annotations: it surfaces assumptions, caps blocking questions at 3, never blocks on them, and hands off prefilled arguments — all things the annotations cannot express. Minor gap: it never says whether anything is persisted or how large the prefilled payload is.

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 imperative 'Call this FIRST' is front-loaded, and every clause maps to a real output or rule rather than filler. The single long enumeration sentence is dense but each listed artifact is distinct; it could be split for scanability, which keeps it off a 5.

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 carries the return-value burden and does so by enumerating the response sections, and it clarifies downstream handoff via prefilled arguments for the next tools. Slightly short of complete because the 'events that matter for this audience' and 'compliance notes' are not given scope or size, and the handoff format is unspecified.

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 only 57%, and the description compensates by naming the semantic dimensions it extracts (niche, product, platforms, regions, currency, offer, deadline) and by noting that platforms and regions are accepted in any spelling or format. The fuzzy-tolerance rule is information the schema, whose platform descriptions list aliases but not the tolerance guarantee, does not fully convey.

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 states a concrete role — an intake/parse step that takes the user's raw request and returns a structured understanding plus routing artifacts. It enumerates exactly what comes back (niche, platforms, regions, events, compliance, landing page direction, prefilled args for next tools), which makes it unmistakable against siblings like event_calendar or content_plan.

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 with whatever the user wrote, even if vague or misspelled" is an explicit ordering constraint plus an input-quality rule, and the example phrase removes any doubt about what to pass. It also resolves the follow-up behavior: questions are never blocking, so the agent knows to ask at most 3 and continue with defaults rather than halt.

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 and openWorldHint, so the safety profile is covered. The description adds genuine behavioral value beyond that: it flags sensitive topics brands must not use and marks trends matching the niche, which tells the agent what the output does. It says nothing about freshness, rate limits, or result volume, so it stops short of a 5.

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?

It is a single front-loaded paragraph that leads with the data sources and ends with use cases — no filler. The three-part enumeration is slightly dense but each clause carries information.

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 only 3 params, no output schema, and no nested objects, the description does the needed work by enumerating the three data categories returned and what the flags mean. It leaves the response shape and the interplay between 'days' and the trend data unstated, which is a modest gap for a read-only aggregation 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%, so all three parameters are already documented in the schema, including that 'places' accepts countries/cities/continents and that 'niche' marks fitting trends. The description largely restates those semantics ('per country', '100+ countries', 'fit the niche') rather than adding new meaning, 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?

The description names three concrete data sources (Google Trends top searches per country, public holidays, Wikipedia reading) and the framing 'live data for content ideas'. That is far more specific than a tautology, but it never contrasts itself with the obvious sibling event_calendar or content_plan, so an agent must infer the boundary.

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 gives clear use contexts: 'make posts timely, plan around public holidays, and spot trends worth a quick story or reel'. There are no when-not-to-use conditions and no named alternatives, which keeps it below a 5.

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