TORDO — Mercado Público de Chile

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

No annotations are provided, so the description carries the burden, and it delivers a genuinely non-obvious behavioral trait: each result carries a transaction count that signals whether the later price lookup will be reliable. It omits matching semantics (fuzzy vs exact), pagination behavior, and what happens on no match, which keeps it short of a 5.

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?

Three tight sentences, front-loaded with the action, then the sequencing rationale, then the reliability signal. Every sentence contributes; there is no restatement of the title.

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?

The tool is a simple two-parameter search and an output schema exists, so return structure need not be explained. The description still adds the meaning of the returned counts, but leaves `limite` semantics and empty-result behavior unaddressed.

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%, so the description must compensate. It conveys the meaning of `texto` implicitly ('a partir de su nombre') but says nothing about `limite` (default 20) or the result-count cap it controls. Partial coverage of two undocumented parameters lands at the 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 verb and resource: find a product's ONU code from its name. It also explains why the tool exists (the catalog is code-based while users speak naturally) and names the sibling it feeds into (`precio_de_producto`), so an agent can place it precisely.

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?

Explicitly positions the tool as the required prior step to `precio_de_producto` and gives the condition that selects it: the user supplies a name, not a code. Nothing is left to inference about ordering.

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?

No annotations are provided, so the description carries the full behavioral burden. It describes the returned content and implies a read-only aggregation, but it does not mention permissions, rate limits, side effects, or whether the call is safe to repeat. This is adequate but leaves clear gaps for a composite tool.

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, well-structured sentence with a front-loaded purpose clause followed by a colon list of outputs and a usage directive. Every element earns its place and there is no redundant text.

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 composite tool with an output schema and no annotations, the description gives a solid overview of what is returned and when to use it. However, it fails to explain the only input parameter, and it omits any behavioral details such as safety or limitations, leaving a notable gap.

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 'codigo' is never mentioned in the description. The agent receives no clarification of what identifier to pass or its format, so the description fails to compensate for the missing schema documentation.

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 exactly what the tool delivers: buyer profile, preparation window assessment, usual competitors, and price bands with confidence. It explicitly tells the agent to use it instead of chaining several tools, which directly distinguishes it from the sibling tools buscar_productos, perfil_de_comprador, and precio_de_producto.

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 a clear context—deciding whether to bid on a tender—and explicitly says 'Úsala en vez de encadenar varias herramientas', naming the alternative approach. However, it does not state when not to use it or any edge cases, so it falls short of full when/when-not guidance.

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 behavioral burden. It discloses the analytical content the tool surfaces (transparency, award ratio, risk signals), which is useful context, but says nothing about whether it is read-only, what permissions or identifiers are needed, or how it behaves operationally.

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 what the tool computes and followed by the decision purpose. No filler, though the second sentence is somewhat marketing-flavored rather than operational.

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?

An output schema exists, so return values need not be spelled out, and the description roughly characterizes the outputs. However, for a single-parameter tool it leaves the parameter unexplained and provides no operational or selection context, so it is only minimally 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 parameter organismo_id has no description in the schema. The description never mentions the parameter, so it does not compensate for the coverage gap; an agent must infer that organismo_id identifies the buyer being profiled.

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 specifies what the tool reveals about a public buyer: its transparency history, its call-to-award ratio, and risk signals. That is a concrete content scope, clearly distinct from the product- and price-oriented siblings. It lacks an explicit verb+resource framing, but the purpose 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?

It gives one clear use case ('decidir si conviene trabajar con él antes de mirar el precio'), which implies the decision context. It does not name alternatives or state when not to use it, so guidance 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?

With no annotations, the description carries the full burden and does disclose output content (percentiles 10-90, data level, confidence, sample size) plus the data-source fallback logic, which is real behavioral context. It does not mention auth requirements, rate limits, or whether missing-data cases return empty vs error, leaving some gaps.

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, front-loaded with what is returned and followed by the filtering behavior. No redundant restatement of the title; both sentences earn their 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?

An output schema exists so return values need not be spelled out, and the two-parameter surface is small. The description covers both parameters' semantics and the fallback behavior; the main omission is the safety/read-vs-write profile, which no annotation supplies.

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 compensate and largely does: it clarifies codigo_producto is a UN code ("código ONU") and explains exactly what organismo_id does via the fallback rule. Syntax/format details for the code are still absent, but semantic meaning is conveyed for both 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?

States a specific resource and scope: historical price bands (percentiles 10-90), data level, confidence and sample size for a product identified by UN code. This is clearly a price-lookup tool and is distinguishable in subject matter from siblings like buscar_productos or perfil_de_comprador, though it does not name or contrast them 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?

The second sentence gives useful behavioral guidance (use organismo data first, fall back to sector/country when insufficient), but there is no explicit when-to-use / when-not-to-use statement and no routing against the sibling tools. Usage is implied rather than prescribed.

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