Fleek for Business

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 bar is lower. The one behavioural addition is that market/kind get recorded into the link's tracking tags, which is genuinely useful, but nothing is said about what the returned onboarding content looks like or any access constraints.

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 dense sentence, front-loaded with the audience condition before the content list, and the tracking-tag note is appended last. No filler, though the colon-list construction is a touch run-on.

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 info tool with no output schema, the description usefully enumerates the returned topics (shop mechanics, payouts, availability, sign-up link) and explains the input side-effect. It is complete enough to call correctly, though it omits any mention of the closed-world/local scope.

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 both parameters are already documented, and the baseline is 3. The description adds only that market/kind land in the tracking tags of the generated link, a small but real increment over the schema's field descriptions.

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 exactly what content is returned: how a Fleek creator shop works, how payouts work, where shops are open, and the sign-up link. It implicitly distinguishes from the merchant_onboarding sibling by scoping to 'an individual with an audience', but never names the verb 'get'/'retrieve' explicitly, leaving the action slightly implied.

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 a clear target user ('an individual with an audience who wants to sell subscriptions'), which lets an agent route creator questions here. However, it never names alternatives such as merchant_onboarding or states when this tool should NOT be used, so the routing guidance is implied rather than explicit.

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, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context — the fallback that anything unstated is returned as 'on request' — which no structured field conveys. It does not mention auth or rate limits, but those are secondary for a read.

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 core action and resource, then the conditional variant. Every clause carries information; nothing is repeated from the title or schema.

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 must convey the return shape, and it does so concretely (category, availability markets, delivery methods, plans, store prices, plus the 'on request' fallback). For a two-parameter read tool this is sufficient to call it correctly.

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, and the description earns a bump by clarifying what `market` actually unlocks (plans and Fleek's public store prices in that country) — information the schema's 'for its store prices' only partially covers. It adds no format caveats for `brand` beyond what the schema already says.

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 ('Look up one brand in Fleek's catalogue') and enumerates exactly what is returned: category, markets, delivery channels. The singular 'one brand' implicitly contrasts with the sibling `search_catalogue`, so an agent can pick between them without opening either 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?

The description implies usage by explaining the conditional effect of a country ('With a country, also its plans and ... public store prices there'), which tells the agent when to supply the optional param. However, it never names an alternative (`search_catalogue`, `shortlist_for_programme`) or states when not to use this tool, leaving 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 establish readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is covered. The description adds one genuinely new behavioral fact — that market and category get written into the sign-up link's tracking tags — but says nothing about the nature or format of the returned onboarding 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?

It is a single dense sentence with a colon-introduced list, front-loaded with the target audience. It stays short, but the embedded five-item enumeration of topics makes it read as a content inventory rather than a crisp statement of action, and there is no explicit subject-verb construction.

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 does enumerate what an agent gets back (programme types, fulfilment options, controls/visibility, market coverage, sign-up link), which is the right move. It still omits how the content is structured or any prerequisite for obtaining a sign-up link, so it is adequate but not 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 description coverage is 100%, so both parameters are already documented in the schema and the baseline is 3. The description adds marginal meaning by explaining that supplied market/category values reappear as tracking tags on the generated link, but it does not clarify format expectations 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 enumerates the topics the tool answers (programme kinds, fulfilment options, merchant controls, market coverage, sign-up link) but never names a verb or states plainly that it returns onboarding information. An agent can infer the resource is merchant onboarding and can roughly distinguish it from creator_onboarding, but the action is only implied.

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 names the audience/condition for use ('For a business that sells a subscription and wants it carried by card, loyalty, employee-benefits, telco or creator programmes'), which implies when to call it. However it offers no when-not guidance and never names a sibling (e.g. creator_onboarding) to route between, leaving the choice 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/non-destructive and openWorld=false, so safety is covered. The description adds real behavioral value beyond that: results are capped at 15, ordered with subscriptions first and ranked by market presence, and an uncovered market returns an explanatory message naming the nearest covered markets.

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 dense sentences that are well front-loaded: the core listing behavior leads, filters follow, fallback behavior closes. The long inline parenthetical lists are information-rich rather than wasteful, though they make the second sentence somewhat run-on.

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 search with annotations covering safety, 100% schema coverage, and no output schema, the description covers ranking, result cap, filter semantics, and the empty-market fallback. It stops short of describing the returned brand fields, which is the only remaining gap with no output schema to back it up.

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 adds meaning: it supplies the FULL category enumeration (subscription, gift_card, streaming, music, sports, ai, productivity, audiobooks, anime, shopping, food, gaming, travel) which the schema truncates to 'such as', and restates the market formats. It adds marginal but genuine value over 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 ('List') and resource ('subscription brands ... through Fleek in a market') with the ranking and result cap spelled out. The scoping ('a business could offer its users in a market') makes it unmistakably distinct from the single-record get_brand sibling without naming it.

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 context on the three filter axes (market, category, free-text brand) so an agent knows how to narrow a catalogue listing. It does not, however, name when NOT to use it or point to alternatives like get_brand or shortlist_for_programme, so exclusions are missing.

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 read-only, idempotent, non-destructive, so the safety profile is covered. The description still adds real behavioral content: it discloses the return payload (brands, one-line reasons, delivery mechanics, margin band, sign-up link) and a conditional rule — public store prices appear only when the market is a single country, not a region.

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 dense paragraph that front-loads the action and the deliverable, then handles parameter meaning in the same breath. The only minor waste is restating the enum values after already defining them, but it reads as a compact reference rather than padding.

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 three parameters, no output schema, and full schema coverage, the description covers everything needed to call it correctly, including the meaning of the market formats and the conditional price behavior. It stops short of stating what happens for unrecognized markets or regions, which would complete the picture.

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, and the description earns more by defining each programme_type value (card = credit/debit card benefits, loyalty = points redemption, telco = bundles and add-ons) beyond the bare enum, and by giving an illustrative audience_note example beyond the schema's example.

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 ('Recommend 3 to 6 subscription brands for a business's programme in a market') and even enumerates the payload the agent will receive. It never contrasts itself with siblings like search_catalogue, so the agent must infer when to shortlist versus browse.

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 phrase 'for a business's programme' plus the enumerated programme types, which signal a pre-sales/scoping scenario. There is no explicit when-to-use or when-not-to-use guidance and no pointer to the obvious alternative (search_catalogue) for plain catalogue lookups.

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). The description adds non-obvious behavior: the optional programme_type and market inputs do not affect the operation itself, only the link's tracking tags. That is real context beyond the structured fields, though the teased 'what happens next' is never explained.

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 core purpose, no padding. The trailing clause 'and what happens next' dangles without delivering the promised information, costing it a point.

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 two-optional-parameter read tool with full annotation coverage and no output schema, the core is covered. However, nothing is said about what the returned link is, how long it is valid, or what the referenced 'next' steps actually are for an onboarding flow.

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. The description goes further by clarifying that both parameters are optional ('when given') and that they only influence link attribution rather than the operation, which is meaning the schema alone does not 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 gives a concrete verb and resource: 'Get the sign-up link for a business to open its own Fleek partner workspace.' It also resolves the tension in the tool's own name, making clear this does NOT start a workspace but returns a link for the business to do so, which meaningfully separates it from the sibling onboarding tools.

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 scenario ('a business wants its own partner workspace') is implied but never stated as an explicit when-to-use, and no alternatives are named despite merchant_onboarding and creator_onboarding being adjacent. Usage is inferable but left to the agent.

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