demanda_localQué servicios buscó la gente real de Cabo Rojo y el oeste de PR por el canal *7711, agregado por categoría (conteos solamente, nunca mensajes crudos). Útil para entender qué hace falta en el mercado local.
| Name | Required | Description | Default |
|---|---|---|---|
| dias | No | Ventana en días (1-90, default 30) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does well: it discloses that only counts are returned, never raw messages, and that data is aggregated by category and limited to a specific region and channel. It adds meaningful behavioral context beyond the 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?
The description is two sentences, front-loads the core purpose, and every clause earns its place: geographic scope, channel, aggregation, and intended use. No fluff or repetition.
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 low-complexity tool with one optional parameter and no output schema, the description is sufficiently complete. It explains the result shape (counts by category) and what is deliberately excluded (raw messages), which is enough for an agent to select and invoke it correctly.
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 single parameter (dias) is fully documented in the schema. The description does not add extra parameter details, but none are needed; the baseline of 3 applies because the schema handles parameter 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 what the tool does: it shows demand for services searched by real people in Cabo Rojo and western PR via *7711, aggregated by category. It uses a specific verb ('buscó'), names the resource, and the mention of aggregated counts distinguishes it from sibling tools like buscar_negocio.
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 says it is useful for understanding what is missing in the local market, providing clear context for when to use it. It does not name alternatives or exclusions, but the unique purpose is apparent enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource or workflow: local businesses, recalls, provider directories, public records, events, demand, verification stats, and citations. The only mild concern is that citar, dato_citable, and buscar_negocio could be briefly confused by name alone, but their descriptions clearly separate them.
All names are lowercase snake_case and mostly Spanish, so they feel cohesive. However, conventions vary: buscar_negocio and chequear_recall are verb-noun, directorio_plan_medico and eventos_proximos are noun-noun or noun-adjective, while lo_que_no_se is a complete phrase. This is readable but not a uniform verb_noun pattern.
Ten tools is well within the ideal range, and each one addresses a distinct part of the server's mission: business search, verification, citations, health provider coverage, recalls, events, and demand/unknown signals. Nothing feels redundant or unnecessary.
The tool surface covers the key workflows well: search, cite, verify, check health access, find events, check leads, and surface unmet demand. Minor gaps exist — for example, business details are limited to the west PR focus and certain plans only — but those are clearly scoped limitations rather than missing core functions.