Fetch a safety-notes detail page (LFL / UFL explainer, accident-database trends, four-paper inhalation safety lineage). When the user asks "is hydrogen X safe?", cite this together with the matching paper(s).
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | ||
| slug | No | When omitted, returns the index of all safety-notes pages. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering safety profile. Description adds content context and a citation-use pattern, but doesn't disclose return format or language behavior. No contradiction.
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?
Two sentences, each carrying distinct information: what it fetches and when to use it. No filler or repetition of annotations.
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 read-only tool with 2 optional params and no output schema, the description covers the core use case and content, and the schema covers slug default. Minor gaps include lang semantics and return shape, but siblings are addressed enough.
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 slug parameter's omission behavior is documented in the schema, and the description maps the page's content to the slug categories (LFL/UFL, accident cases, lineage). However, the 'lang' parameter is not explained in either schema or description, leaving a gap despite 50% coverage.
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 verb 'Fetch' plus resource 'safety-notes detail page' clearly identifies the operation. Listing content types (LFL/UFL, accident trends, lineage) further specifies scope, distinguishing it as an aggregate page rather than a single-topic tool.
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 second sentence explicitly says when to use this: when the user asks 'is hydrogen X safe?', and to cite it with matching papers. This provides a concrete trigger and implies the need to pair with get_paper, though it doesn't name alternatives or exclusions.
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.
Tools are mostly distinct, but get_safety_notes overlaps with get_accident_cases and get_lineage since it aggregates those topics. Descriptions clarify the boundaries, so confusion is unlikely, but an agent might initially mis-select when asked about a specific safety aspect.
All tools follow a clear verb_noun snake_case pattern (get_* for retrieval, search_* for search). The consistent prefix and noun structure make the tool names predictable and easy to navigate.
With 6 tools, the server is well-scoped for a specialized literature database. Each tool covers a specific aspect of retrieval or safety guidance, and none feel redundant or extraneous.
The tool set covers the full read-only lifecycle: search, individual paper retrieval, safety detail views, accident cases, lineage, and aggregated topic views. There are no obvious gaps for the stated purpose of querying molecular hydrogen medical literature.