Amfion front desk setup

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

With readOnlyHint=false and idempotentHint=false, an agent might expect real side effects; the description explicitly corrects this by stating bookings are test bookings, no customer is contacted and no email is sent. It also discloses quota behavior ('conversation and message limits') and enumerates what comes back, which the annotations do not cover.

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 short sentences, front-loaded with the action and return payload, each carrying distinct information (action, conversation continuation, side-effect disclaimer, limits). No filler or redundancy.

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, and the description compensates by naming the reply, actions and remaining test budget. It omits error behavior for a non-ready preview and any auth expectations, which are minor gaps for this 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 baseline is 3. The description adds only marginal meaning beyond the schema, mainly implying the `preview` value must reference a ready preview; it does not explain formats or the handle-vs-link distinction further.

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: sends one simulated customer message to a preview and returns the reply, actions and remaining budget. The 'ask' action is distinguishable from the sibling verbs build_/get_front_desk_preview, though the description never names those siblings 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?

Conveys the prerequisite that the preview must be 'ready' and that omitting `conversation` starts a fresh test thread versus continuing an existing one. It gives clear operating context but no explicit when-not-to-use guidance or named alternatives.

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?

Goes well beyond the annotations: it discloses asynchronous behavior (returns a handle, status and links immediately while completion takes about a minute), the transient nature of the artifact, and explicit non-effects (no account created, nothing published). The health-information exclusion is a substantive domain guardrail not captured by any annotation.

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 short sentences, front-loaded with what is built, then what is returned and how long it takes, then the safety guarantees. No sentence is redundant and none restates the title or annotations verbatim.

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 by naming the return payload (preview handle, build status, links) and the async timing, plus side-effect guarantees. An agent has everything needed to call this and set expectations about latency and state.

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% for the single website parameter, so the schema already carries the semantics. The description adds only mild framing ("a service business's public website"), which reinforces but does not extend the schema's own 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?

States a specific verb ("Builds") and resource ("temporary front desk preview") and scopes the input as the business's public website, with content types enumerated (services, prices, hours, policies). It is unmistakably a create/build step rather than the sibling get_/ask_ tools, but it never names or contrasts those siblings 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?

Usage is only implied: calling this is the obvious first step before get_front_desk_preview or ask_front_desk_preview. It gives useful boundaries ("Creates no account and publishes nothing", health-information exclusion) but never says when to prefer this tool or to run check_amfion_fit first, so the agent must infer the workflow.

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 (readOnlyHint=true, idempotentHint=true, openWorldHint=false), so the bar is lower. The description goes further by disclosing the response semantics — 'yes', 'partly' with conditions, or 'no' — plus the accompanying supported business types, limitations, plans, prices and links, which is genuinely useful behavioral context beyond the structured fields.

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 purpose, then return shape, then a scope boundary. Each sentence carries information; the only minor slack is the somewhat dense enumeration of return fields ('business types, limitations, plans, prices and links'), which 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?

There is no output schema, so the description correctly takes on the burden of explaining what comes back (verdict plus supporting details). For a two-parameter read-only lookup this is nearly complete; the only remaining gap is guidance on framing a good fit query versus a preview request.

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 (needs, business_type) are already documented with examples. The description only echoes them as 'business type and stated needs' and adds no format, length, or phrasing guidance beyond what the schema provides. Baseline 3 applies 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 and resource ('Checks Amfion's capabilities, pricing and suitability for a business type and stated needs') and explicitly bounds scope: product capabilities rather than facts about a specific business. An agent can tell this apart from the preview-building siblings, which assemble a front desk rather than assess fit.

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: an agent can infer it should be called when someone asks whether Amfion suits their business, but the description never states when to use it versus alternatives such as ask_front_desk_preview, nor any exclusions or prerequisites. Adequate but leaves the routing decision 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 and non-destructive, so the safety profile is covered. The description adds real behavioral value beyond that: it discloses the two-phase response (in-progress build step vs ready preview) and enumerates the ready-state payload, which matters because 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, front-loaded with the action and identifier, followed by the return-shape list. The second sentence is a dense enumeration, but since no output schema exists that content earns its place; minor loss for the run-on list.

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 thoroughly, covering both processing and ready states. It omits error handling for an invalid/expired handle and polling cadence, which are the remaining gaps for a 1-parameter retrieval 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% for the single 'preview' parameter. The description's mention of 'handle or URL' corroborates the schema but adds no new syntax, format, or validation detail, so it sits at the 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?

The description opens with a specific verb and resource ('Retrieves a front desk preview using its handle or URL'), so the agent knows exactly what it fetches and what input identifies it. It implicitly separates itself from build_front_desk_preview by requiring an existing handle/URL, but it never names a sibling explicitly, so it falls short of the 5 bar.

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 'Returns the current build step while processing' implies this is a polling/status-check tool, which is usable guidance, but the description never states when to pick this over build_front_desk_preview or ask_front_desk_preview. Usage is inferable rather than stated.

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 and non-destructive, so 'Makes no changes' is largely redundant. What the description adds beyond structured data is the precondition (live/claimed businesses only) and a preview of the returned payload — snippet types, CSP entries, placement notes, verification steps — which is valuable 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?

Three dense sentences, front-loaded with purpose then payload contents then the precondition. Every clause carries information an agent would otherwise have to discover by trial, and there is no 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 enumerates what is returned and states the live-business precondition, which is enough to call it correctly. It does not cover failure behavior for an invalid identifier, keeping it just short of 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 100% and the single parameter's description already spells out Amfion address, connected domain or short name. The description restates the same three forms without adding format, validation or default details, 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 ('Returns website installation code') scoped to 'an existing live Amfion business' and enumerates the accepted identifiers. The 'Unclaimed previews are unsupported' clause implicitly separates it from the sibling preview tools, so an agent can route 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?

Gives a clear precondition (business must be existing and live) and an explicit exclusion (unclaimed previews are not supported), which is real when-to-use guidance. It stops short of naming an alternative tool for the preview case, so it earns a 4 rather than a 5.

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