Start a session and load shared context from other agents, recent sessions, and known failures so you can continue work without repeating past mistakes.
Start a session and load shared context: other agents' work, recent sessions, failures to avoid. Brief by default.
| Name | Required | Description | Default |
|---|---|---|---|
| detail | No | brief (default) or full, which is everything in the store |
Changes observed during successful MCP inspections.
v3.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that this starts a session and loads specific categories of shared context, which goes beyond the readOnlyHint=false annotation. However, it does not clarify side effects of starting a session, whether it replaces an existing session, or what permissions/state changes are involved.
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 definition is front-loaded, compact, and structured: it first states the action and then lists the context loaded, followed by the default mode. Every clause contributes useful information without waste.
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 tool with no output schema, the description gives a useful high-level summary of what context is returned. It remains incomplete about output shape, brief-versus-full differences, and session lifecycle effects, which are important for correct invocation in this session-oriented toolset.
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 100%, and the single detail parameter is fully documented in the schema with its enum and default. The description's 'Brief by default' mirrors schema information without adding further parameter 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?
The description states a specific verb and resource: start a session and load shared context, including concrete content categories like other agents' work, recent sessions, and failures. It is distinguishable from save/record tools, but it does not explicitly differentiate itself from resume_session or search_context.
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 phrase 'Start a session' implies the primary usage moment, but the description does not explicitly say when to use this versus alternatives such as resume_session or search_context. No exclusions or alternative-routing guidance are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.