Stress Test Agent Persona (Murray's Needs-Press)

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is carried by structured data; the description's contribution is the method (adversarial 'Presses' scored against a diagnostic model), which is real added context. It says nothing about cost, runtime for a full battery, or why idempotentHint=false (nondeterministic scoring), which would have been the highest-value disclosure here.

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?

One dense sentence with the action front-loaded and zero filler. The unexplained jargon ('Presses', 'Needs-Press') costs a little clarity against the otherwise tight phrasing.

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?

With no output schema, the description must convey what a call yields, and 'evaluates behavioral stability' is the only hint of a return value. For a three-parameter diagnostic that runs an adversarial battery, an agent gets no sense of result shape or scale, leaving a clear gap.

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 100% and every parameter carries its own enum or length constraint, so the baseline is 3. The description goes slightly further by explaining that 'Presses' are the adversarial prompts the parameters configure, linking pressIntensity to the input schema's injection-battery semantics, though it adds no per-parameter detail.

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 states a concrete verb and resource: it runs a battery of adversarial prompts and evaluates behavioral stability, and it names the diagnostic model (Murray's Needs-Press). That is far more specific than the name alone, though it never ties itself to a nearby sibling such as assess_bias or evaluate_drift, so an agent must infer the boundary.

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 explicit when-to-use, when-not-to-use, or alternative guidance. The adversarial-testing framing implies the context, but nothing tells an agent why it would pick this over the other audit/evaluation siblings, nor what prerequisites (e.g. a valid systemPrompt) make a call appropriate.

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