summarize_tenderReturn the AI summary (title + max two sentences) of a tender in English or German. Labelled as AI-generated; the original notice prevails. Cached per tender and language; generating a NEW summary requires an API key (free tier is enough), anonymous callers get cached ones.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| lang | No | en |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description meaningfully extends the annotations by revealing concrete behavioral traits: summaries are labelled as AI-generated, the original notice takes precedence, results are cached per tender and language, and API-key requirements differ between generating new summaries and retrieving cached ones. This goes well beyond the readOnly/idempotent hints.
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: the first sentence states exactly what the tool returns, and the following sentences add only essential behavioral and access details. Every sentence earns its place with no 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?
Given the simple two-parameter interface and no output schema, the description provides enough for an agent to call the tool correctly: input language, return shape, caching behavior, and access-key nuance. Nothing critical appears 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 0%, so the description must compensate. It does clarify 'lang' by mentioning English or German and hints that caching is per language, but it gives no additional detail about the 'id' parameter beyond the field name. Some meaning is added, but not enough to fully replace schema descriptions.
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 a specific verb ('Return') and resource ('AI summary of a tender'), adding output constraints like title plus max two sentences and language availability. It distinguishes the tool from full-text/search siblings by focusing on the summary rather than the tender itself, though it does not explicitly name or contrast any sibling.
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 context is implied by the description: call this tool when you want the AI-generated summary of a tender in English or German. However, it does not explicitly state when to choose this over get_tender or search_tenders, nor does it provide exclusions or alternative guidance.
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.
fulltext_search and search_tenders both search tenders, which could lead to confusion despite different scopes (stored index vs live previews). get_tender and summarize_tender also overlap since get_tender can optionally include an AI summary.
get_tender, search_tenders, and summarize_tender follow a clear verb_noun pattern, but countries, fulltext_search, and source_status break the pattern with noun-based names. The inconsistency is noticeable but not chaotic.
Six tools is well-scoped for a tender search server: search, retrieval, summarization, country statistics, and source health are each represented without redundancy or bloat.
The core lifecycle of finding, fetching, and summarizing tenders is covered, plus useful metadata and status tools. Minor gaps exist, such as no explicit pagination or sorting controls, but agents can work around them.