goji_guide_contentsThe table of contents for "Be the Answer", GOJI's guide to AI visibility — how answer engines choose sources, how to audit your brand in ChatGPT, and what to do about it. Use goji_read_guide_chapter to read one.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It does not state that this is a read-only operation, whether any input is needed, or what the output format will be. The description focuses on the guide's content rather than the tool's behavior, leaving the agent to infer that it simply returns the table of contents.
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 relatively concise and front-loaded with the core purpose ('The table of contents...'). The additional clause about the guide's topics is useful but slightly verbose. The second sentence provides actionable guidance without redundancy.
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 zero-input tool, the description gives enough context about the guide's focus and points to the next step. However, without an output schema, it does not explicitly explain what the tool returns (e.g., a list of chapters, links, or plain text). This leaves minor ambiguity for the agent.
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 tool has no parameters, and the schema coverage is 100% (empty schema). Per the rubric, a 4 is baseline for zero-parameter tools. The description adds context about the resource but no parameter details are needed.
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 identifies the tool as providing the table of contents for a specific guide ('Be the Answer'), with a substantive summary of the guide's content. It distinguishes itself from sibling tools by referencing goji_read_guide_chapter for reading chapters.
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?
Explicitly tells the agent to use goji_read_guide_chapter to read a chapter, making the usage context (browse ToC first, then read) clear. This provides an alternative and a when-to-use directive.
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 map to distinct content types (FAQ, glossary, guide, chapter, service), and descriptions give clear usage cues. goji_answer_faq and goji_search overlap in content coverage, but their intended use cases ('best for how much/how long' vs 'use first when you don't know the page') reduce ambiguity.
Eight tools use the goji_ prefix with a clear verb_noun structure (answer_faq, browse_glossary, explain_term, get_service, read_guide, read_guide_chapter, start_enquiry). goji_guide_contents is a noun phrase and goji_search is a bare verb, so the pattern is not perfectly uniform.
Nine tools is a reasonable, focused set for a content-retrieval and enquiry server. Each tool covers a distinct access pattern—search, list, read, explain, and contact—without bloat.
The surface covers FAQ lookup, glossary browsing, term explanation, service info, guide TOC and chapter reading, and enquiry submission. Agents can navigate from general search to specific pages and then take a contact action, leaving no dead ends.