MCP Tool-Call Stream

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

Annotations already cover the safety profile (readOnly, idempotent, closed-world, non-destructive). The description adds real value with the transport (SSE) and the 10-credit cost, both absent from annotations. However, it never says whether the tool named in `tool` is executed, which matters because readOnlyHint=true would be misleading if the dispatch can trigger side-effecting tools, and it says nothing about stream lifecycle or termination.

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 purpose sentence is front-loaded and the bracketed metadata lines are terse and each adds a distinct fact (endpoint, required param, cost). Only the "[Required: tool]" line is redundant with the schema, a minor 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 streaming tool with no output schema, the description should explain what events/envelope fields to expect and how the stream ends. None of that is present, and the relationship between `tool`/`args` and actual execution remains unresolved, leaving core behavior undocumented.

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%, so the description must carry the burden. It only repeats that `tool` is required and says nothing about what `tool` should contain (a sibling tool name?), how `args` relates to it, or what `language` changes.

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 names a specific verb and output shape ("SSE-stream of a tool call envelope"), so the agent knows it gets a stream rather than a unary response. But "tool call envelope" is jargon that never resolves whether the referenced tool is actually invoked or just reported on, and nothing distinguishes it from sibling astroway_mcp_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 guidance on when to choose this over astroay_mcp_streaming, astroway_mcp_tools_list, or calling the target tool directly. The metadata block gives group/endpoint/cost, which is operational context but not usage selection criteria.

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