Underpriced AI

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

With annotations covering safety (non-read-only, non-destructive, non-idempotent, closed-world), the description adds substantial behavioral context: auth requirements, eligibility rules for PAY_AS_YOU_GO, balance visibility, Stripe Checkout link behavior, credit expiration, and anonymous fallback. This is rich beyond what the annotations provide.

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 front-loaded and information-dense with no obvious filler, but it is a single long paragraph covering several conditional branches. It is appropriately sized for the complexity, though bullet-like structure would improve scanability.

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, no-output-schema tool, the description covers all key call paths: listing options, purchasing available packs, subscriber-only top-ups, anonymous handling, and where larger options live. Nothing essential for correct invocation appears 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 description coverage is 100%, so the baseline is 3; the description goes further by explaining that PACK_5/15/30 are purchasable here, that PAY_AS_YOU_GO is limited to signed-in plan subscribers, and that larger packs are elsewhere. It does not add syntax or format details, but it meaningfully enriches pack eligibility semantics.

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 specific resource (credit packs for Underpriced AI scans) and the core action (pay/buy), and details what each pack selection returns. It clearly differentiates this payment-related tool from the sibling scan/research tools, which have unrelated purposes.

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 states exactly when each path applies: no pack lists packs and balance, PACK_5/15/30 return a Stripe Checkout link, PAY_AS_YOU_GO is only for signed-in plan subscribers whose plan scans run out, and anonymous callers get the pricing page. Alternatives for larger packs and monthly plans are also routed explicitly.

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 read-only, idempotent, non-destructive behavior. The description adds timing context (comps must have landed, ~20 sec delay), input provenance (scanId from a photo price), and the same-shape-as-price_item return promise, which are not in annotations.

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 pack the purpose, prerequisite, timing, and input source without extraneous text. The phrasing is slightly run-on, but every clause earns its place.

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 re-read tool with no output schema, the description supplies the essential call scenario and return shape via price_item reference. It doesn't cover failure states (e.g., calling before comps land) or the optional cost parameter, but those are partially covered by schema.

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 fully documents scan_id and cost. The description reiterates the scan_id source but adds no new parameter meaning beyond the schema; 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 title provides a specific verb+resource ('Fetch a saved scan's result'), and the description elaborates on the exact resource: the finished result for a signed-in user's account. It distinguishes from siblings by tying the tool to the post-loading scan result and re-reading saved scans, which separates it from price_item and get_sold_comps.

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 states precisely when to call: with account.scanId after price_item reported comps still loading (~20 seconds later), or to re-read any saved scan. It does not explicitly name alternative tools or say 'do not use when...', so it lacks the when-not clarity 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 declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description usefully adds that results are "real" US sales and are the most recent, but says nothing about coverage limits, latency, auth, or how many comps come back.

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, zero filler. The what-and-returns statement is front-loaded and the usage condition follows immediately.

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 single-parameter read tool with full annotation coverage and no output schema, the description conveys the resource, freshness, and returned metrics, which is essentially what an agent needs. Only minor operational detail (volume or limits of returned comps) is absent.

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?

There is exactly one parameter and the schema documents it fully at 100% coverage, including length bounds and formatting advice. The description's "brand, model or pattern, a few specific words" merely paraphrases the schema, so the baseline 3 is appropriate.

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: retrieves the most recent real eBay US sold comps for a query, and even names the returned statistics (count, median, quartiles). That is far more specific than a tautology, but it never names or contrasts with the obvious siblings (price_item, worth_it), 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?

"Use when the user wants to see what actually sold and for how much" gives a clear triggering condition and implicitly separates it from speculative pricing tools. It supplies no explicit when-not guidance and does not name an alternative sibling, so it is context without exclusions.

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 only declare non-read-only, non-destructive, idempotent; the description adds substantial context beyond them: nothing is published, the draft appears on the Sell tab under 'Not live yet', eBay connection state and connect link are returned, and reconnecting lands the user back on the same item. This is exactly the behavioral detail an agent needs.

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-loads the actor precondition and the core action, and every clause carries real information. It is dense with parentheticals and slightly long-winded, but no sentence is wasted.

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 still explains what is returned (review link, eBay connected flag, connect link), the side effects (draft inventory item, no publication), and the user-visible result location. Nothing an agent needs 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 the schema already documents all four parameters, and the description largely restates them (title, list price defaulting to market price, condition). It adds no syntax or format detail beyond the schema, so the baseline of 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 transformation: a photo scan from price_item becomes an inventory item with a draft eBay listing, returning a review link plus connection status. It also disambiguates from the sibling price_item (its input source) and clarifies that despite the name, it never actually publishes.

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?

Specifies the precondition (signed-in user with a price_item scan) and the downstream step (user reviews and publishes in the app). It does not name a specific alternative tool to use instead, but the when-to-use context and the explicit boundary against publishing are clear.

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 not-read-only, open-world, non-idempotent, non-destructive, but the description adds the key behavioral fact that a photo price 'runs a real scan on their account' and requires sign-in, plus the currency/marketplace scoping (eBay US USD vs price.currency). This explains the non-read-only, open-world hints with concrete consequences.

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 what the tool returns, but it is one long clause-stacked paragraph with four parenthetical asides and no visual structure, making it dense to parse. Every element is relevant, yet the absence of structure costs it.

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 full burden and does so: it enumerates the returned fields (estimate, range, comps with links, three list prices with sell chance, net proceeds, verdict), states currency scope, and covers the sign-in requirement for photo scans. An agent has what it needs to call and interpret it.

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 beyond the schema: it ties cost to the worth-it verdict, explains currency depends on whether the call is a description price (USD) or a signed-in photo scan (seller's currency), and reinforces image_url as preferred over description.

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 (price) and resource (secondhand item on eBay) and enumerates the returned artifacts: estimate with range, sold comps, three list prices with 14-day sell chance, seller net after fees, and a worth-it verdict. It clearly implies overlap with siblings like get_sold_comps and worth_it but never names them to route the agent, so it stops short of sibling differentiation.

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 real conditional: use image_url (needs sign-in through the connector, priced in the user's own marketplace/currency) versus falling back to a text description when not signed in, and notes a photo reads better. It stops short of routing among siblings such as get_sold_comps or worth_it, so no explicit when-not statement.

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 (readOnly, idempotent, non-destructive), and 'pure arithmetic in USD' reinforces deterministic, no-network behavior consistent with openWorldHint=false. It also discloses the output verdict set, though it never states the fee rate or whether fees are configurable.

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 tight sentences with zero filler; the output verdicts and the sibling routing are both front-loaded where an agent needs them.

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-param arithmetic tool with no output schema, the description supplies the output categories and the upstream dependency. The only gap is the unspecified fee model, which could matter for trust in the verdict.

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% with both parameters documented, so the schema already carries the semantics. The description restates them in prose ('expected sale price', 'what the user would pay') and adds only the USD unit reminder – baseline 3.

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 computation (seller's net after eBay fees) plus the exact verdict categories returned (worth it / thin / pass) for a given sale price and cost. It is clearly distinguishable from siblings like price_item, which it explicitly defers to.

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 an explicit prerequisite: 'use price_item first when the sale price is unknown,' naming the alternative tool and the condition that selects it. No when-not guidance beyond that, but the routing is concrete.

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