Israel Flower

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

Annotations only say readOnly=false, destructive=false, openWorld=false; the description adds the genuinely important behavior that placing the order does not charge anyone — it creates a held order with a payment link (card, USD, AllPay secure page). That materially changes how an agent should reason about side effects. It omits what happens on failure or whether/how long a hold expires.

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 tight sentences, front-loaded with the action and its payoff, then the payment behavior, then the safety rule, then the pre-check. Every sentence carries information, though the final enumeration reads as a somewhat listy restatement.

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, 8-required mutation with no output schema, the description covers the critical unknowns: the deferred-charge model, the returned payment link and total, and the need to verify delivery details with the person. Remaining gaps (slug semantics, coupon/surprise handling) are modest relative to what is documented, and the return value is already described inline.

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 54%, so several of the 13 parameters (slug, city enum, surprise, delivery_notes, buyer_name/email/phone) rely on the schema alone; the description only enumerates recipient, address, phone, date and card message as items to confirm. That adds a confirmation semantic but no format or selection guidance (e.g. what slug refers to), so it does not fully compensate for 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?

The description states a specific verb+resource ("Place an order") and immediately names the concrete artifact it returns ("get its payment link"), which no sibling offers. An agent can distinguish this from quote, order_status, and delivery_options without opening any 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?

It gives real operating context: the order is only a hold until the person pays, hand them the link and total, and never pay on their behalf unless explicitly asked and funded. It also sets a precondition (confirm recipient, address, phone, date, card message first). It stops short of explicitly routing to siblings like quote for pre-purchase pricing, so not a full 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 and destructiveHint=false, so safety is covered. The description adds genuinely useful operational context beyond that: business rules (no Shabbat or Jewish festival days), operating hours (11:00-19:00 Israel time), and surcharge behavior on certain days. What the returned price/dates represent is disclosed.

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?

One dense but well-structured sentence, front-loaded with the resource ('Where and when we deliver') followed by the returned fields and rules. No filler or redundancy, though the run-on structure could be slightly cleaner.

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 lookup with no output schema and only two optional params, the description adequately enumerates the returned content and the governing rules. The only minor gap is whether omitting date returns the full schedule, but overall it is complete enough to invoke 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?

The city enum is self-documenting with 16 values, and the date param has a schema description plus a format pattern. The description adds invocation semantics for date ('check that day'), clarifying its purpose beyond the bare schema note. Limited remaining gap makes this better than 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?

States a specific resource and enumerates what it returns (cities, price, next delivery dates with surcharge, delivery rules). An agent clearly understands this is a delivery-availability lookup. It doesn't explicitly contrast with siblings like quote or create_order, but the purpose is unmistakable.

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 a date to check that day' gives concrete invocation guidance for the optional date parameter, and the overall context implies pre-order use. However, it never states when to prefer this over quote or create_order, nor what happens when no date is passed (all dates returned?). Usage 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 readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful scope information (it returns all photos, price and attributes), but says nothing about behavior on an unknown slug, error handling, or result size, and there is no output schema to fill that gap.

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?

One sentence, front-loaded with the scope ('one bouquet') followed by the payload list. Every word contributes and there is no filler or restatement of the tool 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, enumerating the returned facets is exactly the right compensating move, and the input wiring is supplied by the schema. Only the probe-it-first dependency on search_bouquets and invalid-slug behavior are left implicit.

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% and the single required param carries its own 'From search_bouquets' note, so the schema does the heavy lifting. The description adds no parameter-level detail beyond implying a single-bouquet lookup, which is the baseline 3 case.

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 resource (one bouquet) and enumerates the returned facets (description, flowers, colours, occasions, price, photos), so an agent knows exactly what it fetches. 'One bouquet' implicitly separates it from search_bouquets, but no sibling is named 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?

No explicit when-to-use or when-not statement. Usage is only implied, and the routing hint lives in the schema (slug 'From search_bouquets') rather than the description, so the agent must infer that search_bouquets must be called first to obtain the slug.

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, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds real value by enumerating the possible status values returned, which matters because there is no output schema, and by implying that both parameters together identify the order. It does not mention auth requirements or not-found behavior.

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 most important information (what is returned) is front-loaded. The parenthetical status list earns its place given the absent output schema, though the sentence reads as a caption fragment rather than an instruction.

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-parameter read-only lookup with no output schema, listing the possible statuses covers the main return-value gap. However, it omits what happens when the order number and email do not match, and gives no hint about privacy or verification implications of looking up an order by a third party's email.

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 50%: buyer_email is documented in the schema, order_number is not. The description names both parameters and conveys that they are used jointly as an identity pair, which is a small semantic addition beyond the schema, but it adds no format, range, or validation detail for order_number.

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 the resource (an order) and precisely what is returned (its status), even enumerating the possible states: awaiting payment, paid, delivered, cancelled. It is a noun phrase rather than a verb+resource and does not explicitly contrast with siblings like delivery_options or create_order, but the scope 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?

No when-to-use guidance, no exclusions, and no alternatives are named. The use case is only implied by the description of the return value; the agent must infer that this is the tracking/lookup tool rather than being told.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that this is a non-committal pricing step ('before placing the order'), but says nothing about whether the quote is guaranteed, how coupon validity is handled, or what happens if the city/date is unserviceable.

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 zero filler; every clause maps to a real dimension of the tool's behavior.

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 and no annotation gaps, the description should explain the shape of the result (currency, breakdown, whether the coupon discount is shown) and error conditions. It gestures at the return value ('exact total') but leaves it thin for a 4-parameter quoting 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 0%, so the description must carry the load — and it does name all four concepts (bouquet, city, date, coupon) in prose. It adds no format, constraint, or enum detail, so it only partially compensates for the undocumented 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 states a specific outcome — the exact total for a bouquet delivered to a city on a date, optionally with a coupon — which is a concrete computational purpose. It implicitly distinguishes itself from create_order via 'before placing the order', though it never names a sibling 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?

'before placing the order' implies the tool is a pre-check step, which is useful contextual guidance. However, no alternatives are named and there is no explicit when/when-not framing against siblings like create_order or delivery_options.

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 description's real contribution is the returned shape (price in USD, photo, page link). However, it says nothing about pagination, result caps, or sort order, and the closing line about handmade Tel Aviv florists is pure marketing with no behavioral 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, front-loaded with the operation and return fields. The final sentence about handmade bouquets earns no place in a tool definition and could be cut without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-required-parameter read-only search, the definition covers what it returns, what can be filtered, and currency. The remaining gap is result-set behavior (how many bouquets come back, pagination), which an agent would want before calling.

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% and the enums are self-describing, so the schema already carries the parameter burden. The description adds a useful mapping ('budget' → max_price_usd) and confirms the four filter axes (occasion, colour, budget, words), but nothing about whether filters combine AND-style or what text matches beyond the schema note.

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 ('List the bouquets for sale') and even names the returned fields (price, photo, link). Distinguishing it from the sibling get_bouquet is only implied through the plural 'list' framing, not stated.

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 the filter dimensions available, which implies when to use it (browsing/filtering a catalogue), but it never explicitly contrasts with get_bouquet or create_order, nor states any exclusions or prerequisites.

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