crossconnect

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It usefully states that each operation proxies a sibling REST API, that offline peers return a fail() with a start hint instead of a traceback, and that speak plays on the agent's own speaker rather than returning audio. It also mentions provider behavior. However, it stays silent on side effects for library_search/media_search, does not cover authentication or rate limits, and gives zero behavioral detail for `voices`. Moderate but incomplete disclosure.

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 description is a single dense paragraph that front-loads the operation list and then details each operation. It packs in URLs, environment variables, provider defaults, and fallback hints, all of which are useful, but the lack of structured bullet points makes it harder to scan. Some details (e.g., exact port numbers) could be moved lower, but no sentence is purely valueless. It is long yet efficient, warranting a middle score.

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?

Given the tool's complexity (8 parameters, no param descriptions, no annotations, and an output schema), the description should cover all operations and parameters to enable correct invocation. It explains three of four operations and several parameters, but completely omits `voices` and the `voice_id` and `limit` parameters. It also never explicitly states the allowed values of `operation`. These gaps make the description insufficient for an agent to fully use the tool.

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 0%, so the description must compensate by explaining parameters. It clarifies `text` for speak, `query`/`tag` for library_search, `query`/`media_type` for media_search, and `provider` for speak. But it never explains the required `operation` parameter as the dispatcher, and it omits `voice_id` and `limit` entirely. The `voices` operation's parameters are also unexplained. Given the 8-parameter schema, nearly half the parameters lack semantic grounding.

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 opens with 'Fleet crossconnects: speak | voices | library_search | media_search' and explains each operation is a proxy to a specific sibling MCP server. This gives a clear verb+resource mapping for four distinct behaviors, making the tool's purpose obvious and differentiating it from its unrelated sibling tools (jlpt, vocab, etc.). The only minor omission is not explicitly tying the required `operation` parameter to these four values, but the implication is strong enough.

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 provides some usage context: it tells when to use speak (with provider choices), library_search (Calibre library), and media_search (Plex library), and it notes the offline peer fail() behavior. However, it does not explain the `voices` operation at all, and it gives no explicit 'when not to use' guidance or alternatives beyond provider choice. Since the siblings are unrelated, that gap is minor, but the missing `voices` guidance is a real defect.

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