threat_model

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

Annotations already declare readOnlyHint/idempotent/non-destructive, so the safety profile is covered. The description earns credit for disambiguating output shape — it produces review prompts, not a scan — which prevents an agent from expecting findings. It stops short of saying what the output schema contains or that no external state is touched.

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, no filler, with the scope constraint and the 'not a scanner' caveat front-loaded. Every clause earns its place.

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?

The output schema exists, so return values need not be described, and annotations cover safety. The gap is input-side: with a fully required 3-param schema and zero schema descriptions, the one unmentioned parameter and the boundary/asset semantics leave an agent guessing how to populate the call.

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%, so the description must carry the load, and it only gestures at 'assets' and 'trust boundaries' by name. The required `dataClassification` parameter is never mentioned, and nothing conveys format, cardinality limits (max 15 assets / 30 boundaries), or what a 'boundary' string should contain.

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 artifact: 'Create STRIDE review prompts' scoped to 'explicitly supplied assets and trust boundaries.' That distinguishes it reasonably well from sibling review tools like code_review_architecture or well_architected_review, though it never explicitly names an alternative.

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?

'for explicitly supplied assets and trust boundaries' implies the caller must already have enumerated the model inputs, and 'Review aid, not a scanner' implies usage context. But there is no explicit when-to-use/when-not or routing to a sibling such as well_architected_review or architect_panel.

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