PrecioSano

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

Annotations only declare readOnlyHint and openWorldHint=false, so the description carries real added weight: it discloses result ordering (cheapest first), that stock is included, that alternative brands are returned, and a data-freshness caveat ('prices refresh every 6 hours: don't memorize them'). That freshness/ordering context is exactly what annotations cannot convey.

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 what the tool returns, then accepted inputs, then a freshness caveat. No filler and every sentence carries information an agent needs.

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 characterize the return payload, and it does: prices, stock, and same-active-ingredient alternatives in ascending price order. It is slightly thin on edge cases (unknown drug, how many pharmacies are covered), but otherwise complete for a one-parameter read tool.

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 single parameter's description already supplies examples for all three accepted forms (brand, active ingredient, name with dose), which the prose merely restates. Baseline 3 is appropriate since the schema does the heavy lifting.

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: prices of a medication across Chilean pharmacies, sorted cheapest-to-most-expensive, including stock and alternative brands with the same active ingredient. It is immediately distinguishable from a generic lookup, though it never explicitly contrasts itself with siblings like ficha_medicamento or marcas_mismo_principio, whose territory it partially overlaps.

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 implied (call this to get prices), and it usefully lists accepted input forms and warns that prices refresh every 6 hours. However, it gives no explicit when-to-use vs when-not guidance and never names an alternative tool for cases where the user wants drug info rather than price.

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 openWorldHint=false, covering the safety profile. The description adds useful behavioral context by disclosing the data source (MINSAL) and the shape of the result (address, phone, map), which the agent cannot infer from annotations alone.

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 dense sentence with no filler, front-loading the resource and its time/geographic scope before the source and returned fields. 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 one-parameter read-only lookup with no output schema, the description is nearly complete: it names the scope, source, and returned fields. Only minor gaps remain (e.g., result ordering, whether results are limited), which are not essential for correct invocation.

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 single 'comuna' parameter is fully documented in the schema (100% coverage) with examples ('Providencia', 'Viña del Mar'). The description adds no syntax or format detail beyond what the schema already provides, 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 resource (on-duty pharmacies), precise scope (today and open now, within a Chilean comuna), the data source (MINSAL directory) and the returned fields (address, phone, map). This clearly distinguishes it from the sibling tools, which concern drug pricing and medication records, not pharmacy locations.

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 phrase 'hoy y abiertas ahora' implicitly tells the agent this is for finding currently open on-duty pharmacies, giving clear context for when to reach for it. It does not name alternatives or exclusions, but the siblings are topically unrelated, so no explicit routing is needed.

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 (readOnlyHint=true, openWorldHint=false), so the bar is lower, but the description adds no behavioral context: no mention of data source, freshness, geographic scope, or whether results are paginated or limited. It lists data categories rather than 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?

A single sentence that is compact and free of padding, but it is a bare list of fields rather than a front-loaded statement of purpose, so it is terse without being informative.

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 lookup with no output schema and no annotations explaining return semantics, the description should establish what the tool returns and how it differs from siblings. Instead it only lists data categories and leaves the core function and positioning ambiguous.

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% with the only parameter (remedio) fully documented including examples. The description adds no syntax, format, or constraint details beyond that, 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?

The description enumerates fields returned (price per pharmacy, price per unit, active ingredient, other brands, 30-day price variation) but never states the verb or resource: it never says it returns a sheet/profile for a medication. An agent must infer the function from the tool name and title. It also doesn't distinguish itself from siblings like buscar_precio or marcas_mismo_principio.

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 tool versus alternatives. With siblings buscar_precio (price search) and marcas_mismo_principio (same-ingredient brands), and the description even mentioning price and other brands, the overlap is significant yet no routing rule is given.

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 and closed-world behavior, so the bar is lower. The description adds genuinely useful context beyond them: results are sorted by price ascending and the source is the ISP sanitary registry, which tells the agent what ordering to expect in the output. It stops short of stating whether prices are per pharmacy or aggregated.

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 compact sentences with no filler; the ordering and source information is front-loaded before the value proposition and the disclaimer. The disclaimer is arguably marginal but is short and defensible in a health context.

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, no-output-schema lookup tool, the description covers what is returned, how it is ordered, and where the data comes from. It does not specify pagination or whether prices include pharmacy identity, but nothing critical for correct invocation 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 description coverage is 100% and there is a single parameter, so the schema already documents the argument including an example. The description adds nothing further about the active-ingredient string (e.g., accent handling, brand vs generic names). 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 description states a specific resource and result set: all brands containing a given active ingredient, ordered from cheapest to most expensive, sourced from the ISP registry. That is far more than a restatement of the name. It does not explicitly name its siblings (buscar_precio, ficha_medicamento), so sibling differentiation is only implicit.

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?

"Es donde está el ahorro grande: cambiar de marca rinde más que cambiar de farmacia" implies the scenario where this tool is preferable, giving a soft when-to-use signal. However, no alternative tool is named and no conditions for choosing between this and buscar_precio or ficha_medicamento are given. The closing line about not replacing medical advice is a safety disclaimer, not usage routing.

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