resultados_recientesÚltimas subastas del BOE con resultado oficial (adjudicadas), opcionalmente por provincia, con el remate y el descuento real sobre la tasación (aritmética del BOE). Pública, sin cuenta. Máximo 15.
| Name | Required | Description | Default |
|---|---|---|---|
| limite | No | Máximo 15 | |
| provincia | No | Slug en minúsculas (p. ej. `madrid`) |
| Name | Required | Description | Default |
|---|---|---|---|
| cta | No | ||
| items | Yes | ||
| disclosure | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide read-only, idempotent, and non-destructive hints. The description adds useful behavioral context beyond annotations: it is public, requires no account, is capped at 15 results, and includes specific outcome fields like remate and discount. This is solid additional transparency for safe invocation.
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 compact sentence that front-loads the core purpose and packs in the optional filter, output highlights, authentication requirement, and result limit. There is no filler or redundancy.
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, read-only list tool with an output schema and complete annotations, the description covers the essential agent needs: what is returned, the optional province filter, result cap, and that no account is required. Nothing critical is missing 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 input schema already documents both parameters fully, including the maximum of 15 and the lowercase slug format for provincia. The description only restates 'opcionalmente por provincia' and 'Máximo 15', adding little semantic value beyond the schema's existing coverage.
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 that the tool returns the latest officially awarded BOE auctions, optionally filtered by province, along with the winning bid and discount. This is specific and distinguishes it from general search tools by emphasizing 'resultado oficial (adjudicadas)', though it does not explicitly name a sibling alternative.
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 context: use this for recent, officially adjudicated auctions, optionally narrowed by province. It also notes the tool is public and requires no account. However, it does not explicitly state when not to use it or which sibling tool to prefer for other cases.
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.
Most tools are grouped into recognizable clusters (alertas, checkout, favoritos, notas), but several retrieval/report tools overlap: `fetch` and `subasta` both expose an auction record, and `analisis_subasta` and `informe` both provide analysis. The descriptions give enough distinguishing detail, but an agent must read closely to avoid misselection.
Naming mixes Spanish and English, and mixes conventions: `alertas_crear` and `buscar_subastas` are Spanish compound names, `create_checkout`/`cancel_checkout` are English verb_noun, while `fetch`, `search`, `subasta` and `informe` are bare words. There is internal consistency within clusters, but no coherent pattern across the full toolset.
32 tools is a large, heavy surface for one MCP server, exceeding the 25+ threshold where consolidation is usually needed. Many tools earn their place given the broad platform, but the multiple search/retrieval variants and five checkout lifecycle tools could be streamlined.
The server covers the core domain thoroughly: auction search/retrieval, viability reports, alerts, favorites, registry notes, market statistics, plans/account, and UCP checkout all have lifecycle coverage. Minor gaps exist, such as no explicit report-purchase history and some payment steps being delegated to a browser, but agents can complete most workflows.