catia_set_safety

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

Annotations only tell the agent this is not read-only and not destructive. The description adds the non-obvious asymmetric behavior that the tier can only be decreased programmatically and that raising it requires a human restart with the CATIA_MCP_SAFETY env var — context an agent could not get from any structured field.

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?

Two sentences, zero filler, with the action verb emphasized up front and the hard constraint placed last. Every clause carries distinct information.

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 single-parameter session-setting tool with no output schema, the description covers the operation, its direction, and its irreversibility. It stops short of defining the practical effects of each tier, which is the only remaining gap an agent might want.

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%, but the enum values are self-describing and the description supplies the ordering semantics ('dangerous -> write -> read'). It does not explain what each tier actually permits, e.g. which operations 'read' blocks, so it only partially compensates for the coverage gap.

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 ('LOWER the safety tier of this session') and even names the direction of the operation with the tier ladder. An agent can immediately tell this mutates session safety, distinguishing it from the read-only sibling catia_get_safety_state.

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 explicit when-to-use context ('before a review or when handing the session to a less trusted step') and an explicit when-not constraint ('It can never be raised from a tool call'). Both the use case and the hard limit are stated rather than inferred.

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