MCP Streaming Chat

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description adds two genuinely useful behavioral facts: the response is an SSE stream (not a single JSON body), and each call costs 100 credits at Tier 4. It does not describe stream termination, error events, or partial-failure behavior, but with readOnlyHint/destructiveHint already covering the safety profile this is solid.

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?

One core sentence front-loads the modality and the resource, followed by a compact metadata block (group, endpoint, required param, cost) that each carry real information. No filler or marketing prose.

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?

With no output schema and a nested chart object, the description should say at minimum what the stream emits (text deltas, event types) and how it ends; it only says 'streaming chat completion'. Cost and endpoint are covered, so an agent can call it, but consuming the response correctly is left to inference.

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 coverage is only 33%; message and language (a 21-value enum with a 'uk' default) have no schema descriptions, and the description contributes nothing about them. It only echoes that message is required and chart is optional, without adding format, length, language, or chart-shape guidance that would compensate for the gap.

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: a chat completion delivered over Server-Sent Events, with optional chart context. An agent can tell what it does, but the description never names the non-streaming alternative (astroway_mcp_ai_chat) sitting in the sibling list, so the differentiation is only implicit in the word 'streaming'.

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?

There is no statement of when to use this versus astroway_mcp_ai_chat, astroway_mcp_ai_comparison_coach, or the agent_* tools. The only signal is '[Required: message]' and 'optional chart context', which implies usage but never excludes or routes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.