Get Behavioural Threats

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

With no annotations provided, the description carries the full burden and does so richly: read-only (nothing judged, written, or paid for), runs over the model with no controls applied, enumerates return contents (standing, result, threats, default_questions, grounds), and specifies the decides:false conditions. This is well beyond what structure alone conveys.

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?

Front-loaded with the core purpose, then progressively details outputs and workflow. The structured paragraphs each carry information, though the passage is on the longer side and somewhat redundant in restating the output payload.

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?

Despite an output schema existing, the description still grounds the return shape and decides:false states, and adds the critical downstream workflow. For a read tool on a complex behavioural-analysis surface, nothing an agent needs to call and act on it correctly is missing.

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 50% — model_id is documented but server_version is bare. The description references 'the model' and 'each control objective' generically but adds no syntax, format, or meaning for either parameter, so it neither compensates for the gap nor over-explains. Baseline 3.

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 (read) and resource (possible threats from behavioural analysis) scoped to each control objective of a model. This clearly distinguishes it from neighbours like get_behavioural_model, get_behavioural_links, and get_threat_model without needing to open any schema.

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?

Explicitly frames the result as not-yet-a-finding and directs the agent to relay it to the person with its default questions first, naming answer_behavioural_questions as the follow-up tool and stating the condition (answer settles a default) that removes the threat. That is explicit when-to-use plus a named alternative.

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