replace_guardrail_mcp_servers

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

Annotations already declare destructiveHint and idempotentHint, but the description specifies exactly what is destroyed (any server omitted from the submitted map), how to clear everything (empty object), and confirms repeat-safety of an identical full map. The 'requires guardrail with target mcp_tools' line adds a real precondition not present in the annotations.

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 short sentences, each carrying distinct information: operation, precondition, destructive semantics, workflow, idempotency. The replace-all constraint is front-loaded before the read-first instruction.

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 rich annotations, full schema coverage, nested object structure, and an output schema, the description covers the remaining agent-critical gaps: precondition, read-before-write, destruction semantics, and idempotency. Nothing needed to invoke it safely is missing.

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 100%, including the empty-object-clears semantics, so the baseline is 3. The description reinforces whole-set replacement and the omission-deletes rule, which clarifies intent more than the schema does, but adds no detail on run_on or capability ids.

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 ('Replace the complete MCP-server mapping set for one guardrail') and makes the replace-all scope unambiguous with 'Any existing server omitted from mcp_servers is removed'. This clearly distinguishes it from the single-entry sibling upsert_guardrail_mcp_server without needing to open either 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 a hard precondition ('Requires a guardrail with target mcp_tools'), a read-before-write workflow ('Read list_guardrail_mcp_servers first'), and the clear-all case. It does not explicitly say when to prefer this over upsert_guardrail_mcp_server, so the alternative-selection guidance is implied rather than stated.

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