Recherche dans le corpus Claude News : l'actualité de Claude et d'Anthropic (modèles, Claude Code, recherche, sécurité, business) du dernier mois. Renvoie les articles pertinents avec titre, source, date, catégorie, résumé et URL à citer.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Nombre de résultats (défaut 8, max 25). | |
| query | Yes | La requête de recherche (FR ou EN). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that it searches the last month's corpus and returns specific fields, but does not mention any caveats such as rate limits, authentication needs, or behavior when no results are found. The return format is helpful, but minimal additional behavioral context is provided.
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, well-structured sentence that packs the purpose, scope, and return format without redundancy. It is front-loaded with the main action and all information is relevant.
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 search tool with 2 parameters and no output schema, the description adequately explains the return format and the temporal scope. It lacks details on pagination or sorting, but these are not critical for a basic search. It is sufficiently complete for the tool's complexity.
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%, so both parameters (query and limit) are already documented. The description does not add extra meaning beyond what the schema specifies, such as language support (already in schema) or default limit (also in schema). Baseline 3 is appropriate.
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 the action (search), the resource (Claude News corpus), and the scope (last month, topics). It distinguishes itself from the sibling 'recent_news' by emphasizing query-based retrieval versus likely a recent-list function.
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 implies this tool is for searching when a query is provided, but it does not explicitly state when to use it versus the sibling 'recent_news'. There is no exclusion guidance or mention of alternatives, only an implicit distinction based on the search verb.
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.
The two tools are clearly distinct: recent_news fetches the latest articles, while search_news performs a targeted query with filtering and summarization. No overlap or ambiguity exists.
Both tools use snake_case and end with '_news', showing a consistent theme. However, one uses an adjective (recent_news) and the other a verb (search_news), so the grammatical pattern is not perfectly uniform.
With only 2 tools, the set feels thin for a news-focused server. It is functional but leaves little room for variety; however, the minimal count is reasonable for a narrow, read-only news corpus.
The tools cover the two core user needs: browsing recent news and searching the corpus. No update/delete operations are expected in a read-only news context, so the surface is adequate with minor gaps (e.g., no category-specific filter tool).
