search_articlesSearch this publication's articles by keyword. Returns the best-matching titles, dates, canonical URLs, and short summaries.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (default 5, max 20) | |
| query | Yes | Search keywords |
| Name | Required | Description | Default |
|---|---|---|---|
| total | No | ||
| articles | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description need not restate safety. It adds useful context by mentioning 'best-matching' and the returned fields, but it does not disclose ranking behavior or pagination details beyond what the schema already provides.
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 short sentences with no filler. The core operation is front-loaded and the return details are concise, making it easy for an agent to parse quickly.
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 2-parameter schema, complete schema descriptions, rich annotations, and presence of an output schema, the description is fully sufficient for an agent to select and invoke the tool correctly. No critical information is 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 100%, with both 'query' and 'limit' already documented. The description only reinforces 'by keyword' and adds no meaningful semantic detail beyond the input schema.
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 states a specific verb ('Search'), resource ('this publication's articles'), and method ('by keyword'), and enumerates return fields. It clearly communicates what the tool does, though it does not explicitly differentiate it from sibling tools like 'search' or 'get_article'.
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 when to use this tool (when keyword search over articles is needed), but it offers no explicit exclusions or references to alternatives among the sibling tools. Usage guidance is left largely to inference.
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.
Search and search_articles overlap significantly, both retrieving article matches with slightly different result formats. Fetch and get_article also both return full article text but are distinguished by id versus slug. Descriptions help resolve these overlaps, but an agent could still pick the wrong tool without close attention.
Most tools follow a snake_case verb_noun pattern like get_article and search_articles, but fetch and search are bare verbs, and popular_content is a noun phrase with no verb. The pattern is readable but not fully consistent.
Six tools is a well-scoped set for a publication content gateway: search, retrieval by two identifier types, recent listing, popular content, and article search. Each tool serves a distinct practical need without bloat.
The core content access workflows are covered: search, retrieve full text by search id, retrieve by slug, list recent, and list popular. Minor gaps exist, such as no pagination or filtering, and search_articles results don't explicitly feed into get_article or fetch, but agents can typically work around these.