Underpriced AI

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

Annotations already signal side effects (readOnlyHint=false), and the description enriches this by explaining the Stripe Checkout link flow, the pay-as-you-go card-on-file mechanism, the credit expiration policy, and the signed-in vs anonymous distinction. It fully discloses the operational behavior without contradiction.

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, well-organized paragraph that front-loads the purpose and then covers each case efficiently. No filler, every sentence earns its place, and the structure naturally guides the reader through the input states.

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?

Given the single optional parameter and no output schema, the description fully covers what an agent needs to call the tool correctly: all input behaviors, user authentication states, and the nature of the returned links. Nothing essential 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?

The schema description already covers the pack parameter (100% coverage), but the description adds value by explaining what each pack actually does, what PAY_AS_YOU_GO does, and that leaving it empty lists options. This goes far beyond the schema's enum list.

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 'Ways to pay for Underpriced AI scans,' a specific verb-resource pair that clearly distinguishes it from the scanning/pricing siblings. It then details the exact behavior for each input state, so an agent knows precisely what the tool does.

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 explicitly states what happens with no pack, with a pack, with PAY_AS_YOU_GO, and for anonymous callers, giving complete when-to-use guidance. Though it names no alternative tools, the context makes it obvious this is the payment tool, and no other sibling overlaps.

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 show readOnly, non-destructive, and idempotent, so the safety profile is known. The description adds behavioral value beyond that: the result is not immediately available, comps land in the background, and the agent should wait roughly 20 seconds. It also scopes the operation to signed-in users.

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 first sentence is efficient and front-loaded: 'the finished result for a scan on their account' immediately communicates the purpose. However, the second sentence is grammatically convoluted, especially 'account.scanId a photo price returned', which makes it needlessly hard for an agent to parse.

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?

Given a read-only tool with one required parameter, strong schema descriptions, and helpful annotations, the description covers the essential async timing and one shape. It doesn't describe fallback or error behaviour, but for a simple 're-read a result' action, the guidance is sufficient.

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 floor is a 3. The description exceeds that floor by explaining when and why a particular scan_id is meaningful: it's the account.scanId returned by price_item and should be re-called after a loading delay. It does not discuss the cost parameter, but the schema already describes it.

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 ('fetch') and named resource ('saved scan's result') with a clear scope: a signed-in user's account. It also distinguishes itself from siblings by referencing the account.scanId from price_item, making it clear this is a follow-up read rather than a comps or price creation tool.

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 explicitly tells the agent whether to call: after price_item reports comps are still loading, wait about 20 seconds and call again, or use it anytime to re-read a saved scan. It doesn't enumerate alternatives like get_sold_comps, but the timing and polling guidance is concrete and actionable.

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 idempotent behavior, so the description does not need to restate those. It adds useful behavioral context by specifying that results are 'most recent,' limited to 'real eBay US sales,' and include median and quartiles, giving the agent a good sense of what to expect despite 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 short, front-loaded sentences contain no filler. The first sentence states what the tool does and what it returns; the second gives direct usage guidance.

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-only tool with rich schema documentation, the description is complete. It explains the input style, the output metrics, and the intended use case, and there is no output schema that would require additional return-value detail.

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 query property already provides detailed guidance ('3 to 6 specific words, brand and model first'). The description's mention of 'brand, model or pattern, a few specific words' adds a little color but does not substantially go beyond what the schema already provides, so the baseline of 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?

The description states a specific verb and resource: retrieving the most recent real eBay US sales for a search query, with count, median, and quartiles. It clearly communicates what the tool returns and distinguishes it from the sibling tools, such as list_on_ebay or price_item, by focusing on actual 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 gives a clear usage context: 'Use when the user wants to see what actually sold and for how much.' It does not explicitly mention when not to use it or name alternative sibling tools, but the guidance is sufficient for selecting it correctly.

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 provide idempotentHint, readOnlyHint, and destructiveHint, but the description adds critical behavior: it never publishes, it returns a review link and connection status, and it requires a signed-in user. It clarifies side effects (creating a draft) and non-actions (not publishing), which is essential context beyond the structured hints. No contradiction with 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?

The description is a single, dense sentence that front-loads the audience ('For a signed-in user') and proceeds logically: input, action, output, and non-action. It is efficient with no wasted words, though it is long. Every clause adds information, so it earns a 4 rather than a 5 due to the length.

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 and does explain the return: the review link, whether eBay is connected, and the connect link if not. It covers prerequisites (signed-in user, scan_id from price_item) and clearly states the non-destructive nature. For a creation tool, this is 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%, so the baseline is 3. The description adds extra meaning by noting the price defaults to the market price, which clarifies the price parameter's default behavior not fully spelled out in the schema. It also implies title and condition are overrides, aligning with the schema. This goes slightly beyond 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?

The description states a clear, specific action: turns a photo scan into an inventory item with a draft eBay listing. It explicitly names the source tool (price_item) and the deliverable (link for review/publish), and adds a key boundary ('It never publishes anything') that distinguishes it from any publishing action. This is specific and 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?

The description implies a workflow ('from price_item') and a precondition ('For a signed-in user'), but it does not explicitly state when to use this tool versus alternatives or when not to use it. It names no sibling tools as alternatives, so an agent must infer the context from the mention of price_item. This is adequate but not 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 indicate non-read-only and open-world behavior. The description adds useful context beyond that: it relies on recent real sold comps, computes a 14-day sell chance, net after eBay fees, and only produces a worth-it verdict when cost is provided. It does not mention possible credit costs or other side effects, but it does not contradict the 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?

The description is dense but efficient: one sentence enumerates the full output contract, and a second sentence gives the key input preference. There is no filler or repetition of the schema, though the long first sentence could be slightly easier to parse.

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 a good job of explaining what the agent will receive: estimate, range, comps, list prices, sell chance, net fees, and verdict. It also clarifies image vs description input behavior. It does not specify exact response structure or mention any credit prerequisite, but for an estimation tool it is largely 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 the parameters are already well documented. The description adds some practical nuance by saying to pass image_url whenever one exists and that description alone works but reads less, but it largely reinforces what the schema already states rather than adding substantial new meaning.

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 clearly states the tool's job: estimating what a secondhand item sells for on eBay US, and enumerates the specific outputs (estimate with range, comps, list prices, sell chance, net fees, verdict). This distinguishes it from siblings like get_sold_comps and worth_it, which cover only parts of this output set.

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 clear input guidance, such as providing image_url when available and noting that description alone works but reads less. However, it does not explicitly state when to choose price_item over sibling tools like get_sold_comps or list_on_ebay, so the selection context is implied rather than fully specified.

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 declare readOnlyHint=true and destructiveHint=false, so the tool is known to be safe and non-destructive. The description adds that it performs 'pure arithmetic' (no external calls), which is a key behavioral trait beyond annotations. However, it does not detail the output format (e.g., the exact wording of the verdict or whether it returns profit in addition to the verdict), leaving minor gaps for an agent.

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 two sentences of minimal length, with the core purpose front-loaded and the usage note (price_item) secondary. Every word earns its place without fluff. It is well-structured and easy to scan.

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 simple two-parameter tool with full schema coverage and annotations that signal safety, the description is nearly complete. It explains the tool's role and when to use it)Skip, but it does not specify the exact output schema or the verdict thresholds, which could be useful for agent planning. Since no output schema is provided, a bit more detail on the return format would push it to 5, but current completeness is strong.

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 schema already fully documents both parameters ('cost' and 'expected_sale_price') with clear descriptions and ranges, achieving 100% coverage. The description adds no extra parameter-level detail beyond implying they correspond to 'what the user would pay' and 'expected sale price', which is redundant. The baseline for full coverage is 3, which 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?

The description clearly states the tool's verb ('Net after eBay fees and a verdict') and resource ('for an expected sale price and what the user would pay'), making its purpose specific. It distinguishes itself from the sibling 'price_item' by explicitly noting this is 'pure arithmetic' and not for unknown sale prices, which helps differentiate 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?

The description explicitly states when to use this tool: when both the expected sale price and the user's cost are known, and provides a direct alternative: 'use price_item first when the sale price is unknown.' This gives clear guidance on tool selection, which is absent in many definitions.

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