Read a single session with its full history in token-dense form. Returns all interactions (chat, navigation, search, form, voice). Document chunks and tool calls are returned as references (IDs + titles) - use read_node(vertex_id) or read_tool(tool_id) to fetch full content.
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds valuable behavioral context: the return is token-dense, includes all interaction types, and document chunks/tool calls are returned only as references (IDs + titles) requiring additional calls to resolve. This goes beyond the structured annotations.
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 with no wasted words. The core purpose is front-loaded, and the second sentence provides essential detail about reference-based returns and how to resolve them. Every sentence contributes meaning.
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 single-parameter read tool with an output schema, the description covers what is returned, in what form, and what to do with returned references. It is complete enough for an agent to select and invoke the tool correctly without further clarification.
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 0%, but there is only one parameter, session_id, whose meaning is directly implied by the description ('Read a single session'). The schema already provides the type and UUID format. The description clarifies that the parameter selects one session's full history, which is sufficient for this simple parameter set.
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 the action ('Read a single session') and the specific resource, including the full history in token-dense form. It lists the interaction types covered (chat, navigation, search, form, voice) and distinguishes itself from sibling read tools like read_sessions by focusing on a single session with full history.
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 makes it clear this tool is for reading one session's complete history, which implies it is the right choice when a single session is needed rather than multiple sessions. It also provides explicit follow-up guidance: use read_node or read_tool to fetch full content of references. However, it does not explicitly contrast with read_sessions or state when not to use this tool.
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 targets a distinct resource or metric, and even the closely related analytics tools (e.g. get_top_languages vs get_top_locales, get_top_interaction_sources vs get_top_clicked_urls) are explicitly differentiated in their descriptions. There is no real overlap that would cause an agent to misselect.
The verb prefixes create_, get_, list_, read_, and update_ are used predictably, and there is no mixing of camelCase or other conventions. The main inconsistency is that read_sessions is actually a list operation while list_nodes is the equivalent pattern for nodes, and read_session_detail is the singular read.
At 33 tools, this set is well beyond the 16-25 'heavy' range and far above the typical well-scoped 3-15 range. Many of the get_top_* analytics endpoints are individually distinct but could likely be consolidated into fewer parameterized tools to reduce agent selection overhead.
The read and analytics side is comprehensive, but the management lifecycle has notable gaps: knowledge nodes support create/read/update but no delete, and data sources/tools lack create/delete operations. Agents can work around some gaps, but content deletion is a clear dead end for a knowledge-base management surface.