audit_replication

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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description explains why: it writes per-Blueprint detail to Saved/MCPAudits/ on disk. It further discloses that the tool returns only a SUMMARY plus a report path, which is a non-obvious behavioral trait beyond what annotations convey. No contradiction.

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?

Four tightly packed sentences, front-loaded with purpose, then the three inspection dimensions, then the critical output/read-back behavior, then the alternative tool. The technical identifiers (CPF_Net, FUNC_NetFuncFlags) add precision rather than noise, and nothing is redundant.

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 exists, so the description carries the full burden of describing the return, which it does explicitly (path + summary with blueprint_count, replicated_class_count, replicated_variable_count, rpc_count). It also closes the loop on how to retrieve the full detail, so an agent can complete the task correctly.

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% — recursive, folder_path, and max_results are all documented with defaults and ranges in the schema. The description references folder_path scoping but adds no syntax or format detail beyond the schema, which is the correct baseline-3 case when the schema does the heavy lifting.

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+resource (project-wide replication audit) and enumerates exactly what it inspects: replicated variables (CPF_Net), class replication (AActor::GetIsReplicated on the CDO), and RPC functions. It names sibling tools (get_replication_info / get_actor_replication_info) as the single-actor alternatives, so it is distinguishable without opening a schema.

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?

Gives an explicit when-to-use (sweep every Blueprint under folder_path) and when-not-to-use (for one actor, use get_replication_info / get_actor_replication_info). It also tells the caller they must read the full report back with read_mcp_audit_file, which is a required follow-up step, not just a hint.

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