refine_threat_model

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 extensively details the semantic-preservation guard, reversion of identity fields, semantic_rejections array, re-appending of dropped entities, tombstone behavior with removed=True, and stable CO IDs. This goes well beyond minimal expectations.

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 compact relative to the complexity, leading with the main purpose and then using clear bullet points for behavioral guarantees. Every sentence contributes operational knowledge without filler or redundancy.

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, the description covers versioning, affected entities, preservation and rejection behavior, tombstoning, orphaned controls, and the semantic_rejections return field. Since an output schema exists, detailed return value documentation is not required here.

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 67% (model_id and instruction described, server_version blank). The description adds substantial meaning for the instruction parameter by explaining how it drives a semantic-preservation guard and what happens to proposed changes. It does not address server_version, but the main operation parameters are richly contextualized.

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 uses a clear verb ('Refine') with a specific resource ('existing threat model') and enumerates the affected components (assets, attackers, trust boundaries, control objectives). This clearly distinguishes it from siblings like generate_threat_model (create new) and delete_threat_model (remove).

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 states it operates on an existing model via an instruction and creates a new version. It also provides behavioral constraints ('CANNOT silently replace an entity's identity... or silently drop an entity'), which signal when not to rely on it for targeted edits, though it does not explicitly name alternative tools.

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