dipscout

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

With no annotations, the description carries the full burden and does real work: it discloses the detection methodology (price history, last 7 days, time-weighted median of readings), explicitly warns that the seller's 'was' price does not count, and defines the discount.certainty values and their permissible use. Missing are ordering logic, pagination/truncation behavior, or any rate/completeness limit beyond the parenthetical 'up to 100'.

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 core criterion is front-loaded, which is good, but the seller's 'was' price exclusion is stated twice in near-identical terms ('the seller's was price does not count' and 'The seller's was price on the listing does not support any discount here'), wasting a full sentence. The certainty explanation is valuable but 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?

For an 8-parameter, no-annotation, no-output-schema tool, the description covers the most consequential unknown: the meaning and safe use of discount.certainty, which otherwise would be opaque. It still leaves result ordering, the relationship to the two sibling tools, and any truncation of results unaddressed, so it is strong 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 88%, so the schema already documents busca, idioma, mercado, categoria, preco_maximo and desconto_minimo well. The description adds essentially no parameter-level detail beyond what the schema states, which is acceptable at this coverage level but not above 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?

It states a specific verb and resource ('Lists AliExpress products') plus the defining scope condition (a real price drop proven by our own price history over the last 7 days, excluding the seller's 'was' price). That is a concrete, non-tautological purpose. However, it never distinguishes itself from the sibling quedas_de_preco, whose name suggests an overlapping capability, so the agent gets no routing signal.

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 strong guidance on how to use the results ('verified' MAY be presented as savings, quoting the percentage without certainty misinforms), but that is presentation guidance, not tool-selection guidance. There is no statement about when to call this versus historico_de_preco or quedas_de_preco, and no exclusions or prerequisites.

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?

With no annotations, the description carries the full burden. It usefully discloses that the response includes the number of readings and days of tracking, and explicitly warns when tracking is too sparse to support a drop claim. However, it does not cover permissions, rate limits, or broader response structure.

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 three efficient sentences, front-loading the core purpose and then the output caveat. No sentence is wasted, though it could be slightly tighter.

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 read tool with no output schema, the description gives enough input flexibility and output caveat for an agent to invoke it correctly. It lacks explicit sibling routing, but the core operational picture 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 description coverage is 100%, so the schema already documents both parameters. The description reinforces that produto accepts either a numeric ID or a full product URL, but adds no detail about the idioma parameter beyond what the schema provides.

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 identifies a specific resource and capability: an observed price series for an AliExpress product. It is understandable without opening the schema, though it does not explicitly differentiate itself from siblings like quedas_de_preco or buscar_promocoes.

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 explains accepted inputs (itemId or product URL) and implies relevance to drop-claim validation, but does not state when to use this tool versus the sibling tools. Usage is inferable but not explicitly directed.

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?

Since no annotations are present, the description must carry the full behavioral burden. It does this by explicitly detailing the 'verified' vs 'none' certainty status and warning the agent against misinforming the user. This disclosure of data integrity rules is highly valuable.

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 not wasteful; every sentence contributes critical, non-redundant information (e.g., flash sale caveat, definition of certainty). While verbose, the structure logically builds the definition from calculation criteria to presentation guidelines.

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 complexity of the underlying metrics (time-weighted median, multi-criteria thresholds), the description is remarkably complete. It explains the methodology, the constraints, and the reliability of the results.

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 description does not add unique semantic value to the input parameters (idioma, limite, mercado), which are sufficiently covered by the schema descriptions. It does, however, provide crucial context regarding the tool's outputs which indirectly relates to parameters.

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 is extremely precise, defining exactly what constitutes a 'price drop' (15% and $3 below typical price, or lowest recorded price). This high level of mathematical specificity clearly distinguishes the tool's function from general promotion searching.

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 sets strict conditions for use, such as requiring 3 days of tracking and defining the scope of the data based on time-weighted medians. It manages user expectations about the data quality (e.g., explaining that the seller's listed price is not considered in the calculation).

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