search_articlesSearch the English blog corpus by keyword and return matching articles with their titles and canonical URLs. Use to find Shotlee coverage of a drug, peptide, side effect or topic.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | Keywords, e.g. "ozempic nausea" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden for behavioral disclosure. It does state the return format (titles and canonical URLs) and the language scope (English). However, it does not disclose optional behavior such as pagination, result ordering, or the default/max limit, leaving some uncertainty about the tool's full behavior.
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 sentences, front-loaded with the main action, and contains no fluff. It packs essential purpose and usage context into a concise form.
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 two parameters and no output schema, the description covers the main return elements (titles and canonical URLs) and the intended use case. It could be more complete by noting the limit behavior, but given the low complexity, the current level is sufficient for basic selection and invocation.
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?
The schema covers only 50% of parameters (only 'query' has a description). The description adds meaning for the 'query' parameter (search by keyword) but fails to mention the 'limit' parameter at all, leaving the agent without details on how to control result count. Given the low schema coverage, the description should have compensated but did not.
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 ('Search') with a specific resource ('English blog corpus') and purpose (find coverage of a drug, peptide, side effect or topic). It distinguishes from siblings: calculate_reconstitution is a calculator, get_article retrieves a specific article, while this tool searches across the corpus.
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 explicitly tells when to use the tool ('Use to find Shotlee coverage of a drug, peptide, side effect or topic'). It provides clear context for its intended use case but does not mention when not to use it or explicitly name alternatives (e.g., get_article for a specific known article).
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 clearly distinct purpose: calculate_reconstitution handles dosing math, search_articles finds blog posts, and get_article retrieves a specific article by slug. There is no overlap in functionality, so an agent can easily select the right tool.
All tool names follow a consistent verb_noun pattern with snake_case: calculate_reconstitution, get_article, search_articles. This makes the tool set predictable and easy to navigate.
Three tools is slightly small but appropriate for a niche server that combines a reconstitution calculator with blog content retrieval. Each tool serves a distinct purpose and none are redundant, though the set feels a bit minimal.
The calculator covers the core reconstitution math, and the blog tools allow searching and fetching articles. Minor gaps exist, such as no way to list all articles or handle other types of dosing calculations, but the surface is workable for the intended use case.