searchBúsqueda en lenguaje natural de subastas judiciales del BOE (compatible con la búsqueda profunda de ChatGPT): devuelve results con id, title y url. Pública, sin cuenta. Usa fetch con el id para leer la ficha.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Búsqueda en lenguaje natural |
| Name | Required | Description | Default |
|---|---|---|---|
| results | Yes |
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?
The annotations already declare read-only, idempotent, and non-destructive behavior. The description adds meaningful extra context by stating that the tool is public and requires no account, and by describing the recommended follow-up workflow with `fetch`. This goes beyond what the annotations alone provide.
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 compact and front-loaded: it states the purpose, result shape, access model, and next step in two sentences. Every sentence contributes new information without padding 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 one-parameter read-only tool with an output schema and safe annotations, the description covers purpose, return shape, authentication, and the follow-up call. It is nearly complete, though a brief note on when to prefer this over the sibling search tools would eliminate the remaining ambiguity.
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%, with the single `query` parameter already described as 'Búsqueda en lenguaje natural'. The description repeats this idea but does not add examples, formatting guidance, or constraints beyond what the schema already documents, so it stays at the baseline for fully covered schemas.
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 specifies a natural-language search over BOE judicial auctions and states the returned fields (`results` with `id`, `title`, `url`), so the core purpose is unambiguous. However, it does not explicitly differentiate this from sibling tools like `buscar_subastas` or `buscar_por_codigo`, which keeps it from a top score.
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 provides useful context: it is a public, account-free natural-language search, and it instructs the agent to use `fetch` with the `id` to read the full record. It does not explicitly state when to choose this tool over the other search-related siblings, so usage 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.
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.