refine_threat_model

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

With no annotations provided, the description fully bears the burden of behavioral disclosure. It details the versioning, progress reporting, guardrails for identity rewrites (revert/rejection), entity re-appending on drop, stable CO IDs, and tombstoning. This provides comprehensive insight into the tool's side effects and safety mechanisms.

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 somewhat lengthy but well-structured with bullet points that clearly separate behavioral rules. Every sentence contributes essential information, though a slight trim could improve readability without losing content.

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 and lack of annotations, the description covers most aspects: return values (semantic_rejections), entity preservation, removal handling, and ID stability. However, it omits prerequisites (e.g., model existence) and does not explain the 'server_version' parameter's purpose or default behavior.

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?

The schema description coverage is 67% (2 of 3 parameters have descriptions). The tool description does not add any parameter-level meaning beyond the schema; notably, the undocumented 'server_version' parameter is not explained. For a tool with 3 required parameters, this is a significant gap that the description fails to address.

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 explicitly states 'Refine an existing threat model based on an instruction' and lists the updated components (assets, attackers, trust boundaries, control objectives), clearly distinguishing it from sibling tools like add_asset or edit_attacker by emphasizing it as a bulk update operation that creates a new version.

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 implies when to use refine (for bulk updates) and provides exclusion guidance by stating that removed entities are re-appended and the sanctioned removal path is remove_asset/remove_attacker. However, it does not explicitly contrast with edit_* tools or state when not to use it (e.g., for single-entity changes).

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