Retrieve a JSON snapshot of a live agent event stream to monitor session activity and inspect recent events.
[Capability: available_with_tier_gate; tier: pioneer_plus; API: /api/v1/agent/stream; authority: /api/v1/agent/status] Observe: read a JSON snapshot from the agent event stream for a live session.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| since | No | ||
| types | No | ||
| sessionId | Yes | ||
| agentAddress | Yes | ||
| sessionToken | Yes |
Changes observed during successful MCP inspections.
v5.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds a concrete access requirement not in annotations (tier gate pioneer_plus, authority endpoint), which is genuinely useful. It says nothing about rate limits, snapshot freshness, or what a 'snapshot' means relative to a stream.
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 compact clauses, with the operational verb front-loaded after the capability metadata prefix. The bracket prefix is dense machine-style metadata but carries real gating info; no filler sentences.
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?
No output schema and no description of the snapshot payload shape, ordering, or pagination semantics, and half the parameters are fully undocumented. For a 6-param tool with a zero-coverage schema, the description leaves too much for the agent to guess.
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% across 6 parameters, and the description mentions none of them. The optional limit, since and types filters, which control the snapshot window and are the main source of misuse, get zero explanation anywhere.
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?
States a specific verb and resource: read a JSON snapshot from the agent event stream for a live session. That is far more useful than the name alone. It never contrasts itself with the sibling get_agent_events (snapshot vs. event list), so sibling differentiation is missing.
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?
'for a live session' hints at context but gives no explicit when-to-use, when-not-to-use, or alternative. With a near-duplicate sibling (get_agent_events) in the toolset, the absence of routing guidance is a real gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.