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

With no annotations, the description carries the full behavioral burden. Saying it returns a 'risk score' implies a read-only analysis, but the description never states what the score range means, what input form the message takes, or whether the result includes explanations — all critical for correct invocation.

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?

It is a single front-loaded phrase with no filler, which is efficient. However, it is a sentence fragment rather than a complete statement, and its brevity reflects under-specification rather than disciplined conciseness.

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?

There is no output schema and no annotations, and the description omits how the message is supplied (raw text, ID, object) and how the risk score should be interpreted. For a screening tool with an empty parameter schema, the description leaves too much to inference.

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 tool declares zero parameters, which per the rubric is baseline 4 since there is no schema-level parameter semantics to compensate for. The open additionalProperties schema is not clarified, but there are no named arguments to document.

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 names a specific resource (a message) and a specific output (phishing/social-engineering risk score), so the agent knows exactly what the tool produces. It does not need sibling differentiation here because none of the sibling tools (clean_csv, endpoint_safety, verify_text, etc.) overlap with this phishing-scoring function.

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?

There is no guidance on when to invoke this tool versus alternatives such as verify_text or honesty_audit, which an agent could plausibly confuse with message screening. No preconditions or exclusions are stated.

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