Context Window Supply

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

Adds real context beyond the annotations: it charges nothing itself (the payment happens on Stripe), the link is opened by a person, and card details must never be sent to this server. Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false), so this enrichment is genuine value rather than repetition.

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?

Compact and mostly front-loaded, with the core action stated in the second sentence. The opening 'Checkout is live' is vague filler that does not clearly earn its place, but the rest of the description is tight.

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?

Covers the essential behavior (creates a link, no charge, US-only, no card data) for a tool with no output schema, and annotations handle the safety profile. However it omits the items/country parameter structure and any note on link lifetime or response shape, leaving gaps for an agent assembling a call.

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% at the top level: neither the 'items' array structure nor 'country' is documented in the description beyond the loose 'US shipping only' hint. The nested size/color notes live in the schema, not the description, so the description does little to 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?

States a specific verb and resource: it 'Creates a Stripe checkout link for the order'. That clearly separates it from the read-only siblings (get_product, search_products, get_shipping_quote). The opener 'Checkout is live' is ambiguous noise, but the core sentence 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?

Provides constraints ('US shipping only', 'charges nothing by itself') that imply when the tool applies, but names no alternatives and gives no prerequisites, such as requiring items to come from get_product or a prior shipping quote. Usage is inferred 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 readOnlyHint=true, so 'Read-only' is largely a restatement. The useful addition is disclosing the returned fields (sizes, colors, price), which matters since there is no output schema, but it omits error/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?

Two short sentences, front-loaded with the core action and return contents. 'Read-only' is redundant with the annotation, a small amount of waste, but the whole description is minimal.

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

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

For a one-parameter read tool with no output schema, the description covers the action and the salient return fields, which is roughly adequate. It leaves the parameter semantics and not-found behavior unaddressed, so it is viable 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 0% and the single required parameter, product_id, is never mentioned in the description. The agent gets no hint about the id format or where it comes from (presumably search_products), so the description fails to compensate for the schema 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?

States a specific verb+resource ('Get one product') and signals single-item retrieval, which implicitly differentiates it from the sibling search_products. It does not explicitly name or contrast with that sibling, so it stops short of 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?

No when-to-use statement and no mention of alternatives; the agent must infer from 'one product' that this is a direct lookup after a search rather than a browsing call. Nothing tells the agent when search_products or get_shipping_quote should be preferred instead.

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 annotations only declare readOnlyHint=true, and the description repeats 'Read-only' (no added credit) but goes further by disclosing the actual pricing model — per-item first/each-extra rates for tee, hoodie and sticker sheet. That is genuine behavioral detail an agent needs to interpret the quote; it stops short of covering size upcharges, the 10-item cap, or the response shape.

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?

Extremely dense: one sentence for the return/scope, one for the safety hint, and a compact rate table. Nothing is wasted, though the opening fragment omits a verb, making it slightly telegraphic.

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 quote tool with no output schema, the description does state the three returned values and the pricing rules, which covers the core. It omits currency, how multi-item baskets are aggregated, and the US-only constraint on the country parameter, leaving real gaps.

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 reported at 0%, so the description must carry the load, and it does not. It never explains the items array, that product_id and quantity are required, that size/color are required for tees and hoodies, or why country is a US-only enum — the per-product rates only loosely hint at valid product types.

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 concrete outputs (subtotal, shipping, total) and the scope (US delivery), which is enough to separate it from get_product, search_products and create_checkout_link. It lacks an explicit verb such as 'calculate', but the resource and result are 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?

Usage is only implied: the US-only framing and price table suggest this is called to cost an order before checkout, but no sibling is named and there is no statement of when to prefer this over create_checkout_link or when not to call it (e.g. non-US orders).

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: annotations only say write, non-idempotent, non-destructive, open-world, while the description discloses the full human-in-the-loop flow (a person reviews, replies by email), that no refund is executed automatically, and an explicit security constraint ('never send card numbers'). This is exactly the kind of downstream-behavior disclosure annotations cannot express.

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, front-loaded sentences that each carry weight; the request-vs-refund distinction arrives first. Slight redundancy between 'It only files a request' and 'never refunds anything by itself', but the emphasis is defensible for a safety-sensitive operation.

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 4-parameter write tool with no output schema, the description closes the important gaps: it explains what happens after invocation (human review, email reply) and constrains what data the agent may pass. Nothing needed to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every parameter is already documented (including the Stripe/order number formats and reason examples). The description only restates the required triple without adding syntax, format, or optionality detail, 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+resource ('Files a refund request for a past order') and immediately narrows the scope by clarifying it is a request-filing tool, not a refund engine. None of the siblings (checkout, product, shipping, search) overlap, and the description makes the boundary explicit rather than relying on the reader's 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?

Clearly signals the context of use — a past order needing a refund — and that a human reviews and replies by email, which tells the agent to expect a non-instant outcome. It does not name explicit when-not conditions or alternatives, but no sibling competes for this task.

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 the description redundantly states 'Read-only', so no new safety info is added. It does add domain context (what merch exists) which helps the agent frame results, but says nothing about pagination, result limits, or empty-result 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?

Two short clauses, front-loaded with the action and resource. 'Read-only' is redundant with annotations, slightly wasting space, but overall compact and well-ordered.

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?

A search tool with 0% parameter descriptions, no output schema, and no explanation of result shape or result limits. The description should at minimum clarify how query filters and what a search returns, but instead only describes the catalog domain.

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 0% and neither parameter is explained. The description mentions product types matching the 'type' enum values, but gives no meaning for 'query' (free text? matching against what fields?) or how the two params combine. It partially compensates by listing the type category but leaves query undocumented.

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 (Search) and resource (merch/products), and gives concrete examples (tees, hoodies, stickers) plus the target audience. This distinguishes it from get_product (single item) and create_checkout_link. It doesn't distinguish itself explicitly from siblings in text, but the resource scope is clear.

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 guidance on when to use this versus get_product or the checkout tools. The agent must infer that search is for browsing and get_product is for known IDs. No exclusions, no follow-up flow described.

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