search_articlesSearch Anxiety in Children's editorial corpus by query. Returns title, slug, summary, and URL for matching articles.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Alternate parameter name for `query`. | |
| limit | No | Max results (default 10, max 50). | |
| query | Yes | Free-text search query. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as read-only (readOnlyHint=true). The description adds that results return title, slug, summary, and URL, which is useful. But no further behavioral details are disclosed, such as matching semantics or result sorting. Since the annotation covers the main safety aspect, a 3 is appropriate.
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?
One concise sentence that includes the action, resource, and expected output fields. No filler or redundant content.
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?
With no output schema, the description does explain what the tool returns, which is a key part of contextual completeness. It is a simple search tool with 3 parameters, and the description covers the corpus scope and returned fields. Minor omissions like sorting or edge-case behavior are not critical for this level.
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?
Input schema covers all parameters (query, q, limit) with descriptions, so schema coverage is 100%. The description itself does not add parameter-level detail beyond the schema, but the baseline of 3 applies because the schema carries the semantics.
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?
Description states a specific action ('Search'), a specific resource ('Anxiety in Children's editorial corpus'), and the output fields returned. This clearly differentiates from siblings like list_articles (which implies listing all) and get_article (which implies fetching a single 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 use case is implied: use when you need to find articles by a free-text query. However, no explicit guidance is given about when to use this versus list_articles or get_article, and no exclusions or alternatives are mentioned.
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.
Each tool has a clear, distinct purpose: fetching a single article, listing articles, searching articles, citing, crisis resources, and site info. No two tools could be easily confused, even list and search are differentiated by query vs. pagination.
All tool names follow a consistent verb_noun pattern (cite_article, get_article, list_articles, search_articles, etc.). The convention is uniform and predictable.
With 6 tools, the set is well-scoped for an article library, covering reading, searching, listing, citing, plus crisis and site info. No redundancy or bloat.
The tool surface covers the core library workflow: discover (list/search), access (get), cite, and contextual info (microsite). The inclusion of crisis resources is a thoughtful addition for the domain. No obvious gaps for a read-only content library.