revalidate_threat_model_entities

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

With no annotations provided, the description carries full responsibility for behavioral disclosure and does so thoroughly. It reveals the two-pass validation (first-pass fast check, deeper review only for flagged entities), non-destructive behavior ('an entity that should be removed is left in place'), side effects (saved as a new model version, controls carry forward), cost implications ('may consume credits'), and return value (envelope with accepted/model). This goes well beyond a simple read/write classification.

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 longer than a single sentence but is structured into three focused paragraphs: what it does, when to use it, and side effects/returns. Every sentence adds functional or risk-relevant information, with the key 'without regenerating the whole model' placed early. The length is justified by the complexity of the operation.

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 the presence of an output schema (signaled but not shown), the description still covers important contextual aspects: non-destructive semantics, versioning, carry-forward of controls/objectives, credit consumption, and the exact return envelope. It also explains the trade-off compared to full regeneration, making the description complete for an agent's decision-making.

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 only 50%: model_id has a description but server_version is undocumented. The tool description does not add any meaning for server_version or further elaborate on model_id beyond the schema. Since the schema leaves half the parameters unexplained and the description does not compensate, the agent lacks clarity on a required input.

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 opens with a specific verb phrase 'Re-run quality validation on a threat model's existing assets and attackers' and clearly scopes it to 'existing' entities, differentiating it from generation or refinement tools. It further distinguishes by explicitly stating 'without regenerating the whole model,' which sets it apart from sibling tools like generate_threat_model and refine_threat_model.

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 gives an explicit use case: 'Use this to apply validation improvements to an already-generated model, or to clear stale quality warnings' and provides a clear when-not by contrasting with regeneration. However, it does not name specific alternative tools (e.g., 'use refine_threat_model instead'), though it makes the context unambiguous enough for an agent to select correctly.

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