Ambient Code Platform MCP Server

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

No annotations provided, so description carries full burden. It mentions output formats (JSON/Markdown) which adds context, but fails to disclose safety characteristics (read-only vs destructive), error behavior when session doesn't exist, or whether large transcripts are paginated. 'Retrieve' implies read-only but doesn't explicitly confirm it.

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?

Single sentence, front-loaded with verb. Efficient structure without redundancy. However, the space could have been used more effectively—e.g., adding safety hints or distinguishing from acp_get_session—rather than restating the format enum values already present in the schema.

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 3 simple parameters (100% described in schema) and relatively straightforward retrieval purpose, the description covers the basics. However, lacking annotations and output schema, it should do more to distinguish from semantic siblings (acp_get_session) and disclose behavioral traits like error handling or content scope (e.g., does it include system messages?).

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 100%, establishing baseline 3. Description adds minimal semantic value beyond schema: it connects 'JSON or Markdown format' to the transcript output, but doesn't expand on the 'project' parameter's role in multi-tenant scenarios or provide examples. Adequate but not enriching.

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?

Clear verb ('Retrieve') and resource ('conversation history for a session'). The mention of 'conversation history' effectively distinguishes this from siblings like acp_get_session (likely metadata) and acp_get_session_logs (system logs). However, it doesn't explicitly clarify the distinction from acp_get_session, which could cause confusion.

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?

No guidance on when to use this tool versus acp_get_session or acp_get_session_logs. No mention of when to prefer JSON versus Markdown format, or prerequisites like session existence. Agent must infer usage from parameter names alone.

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