ATENA Decision Intelligence

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

No annotations are supplied, so the description carries the full disclosure burden. It does describe the payload (capabilities, decision types, endpoints, guidance), implying a non-destructive read, but it says nothing about idempotency, side effects, or whether this returns static documentation vs. live state.

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?

A single front-loaded sentence with the verb and resource first and the returned contents enumerated after. No filler or redundancy.

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 parameters and no output schema, the description usefully enumerates what the call returns (capabilities, decision types, endpoints, guidance), which partially compensates for the missing output schema. Only the absence of any call-ordering guidance relative to atena_decide keeps it from being fully complete.

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 takes zero parameters, so there is nothing for the description to clarify; baseline 4 applies. No parameter-related gaps exist.

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 ('Return') and resource ('ATENA capabilities') and enumerates the returned content: decision types, endpoints, and agent-use guidance. It is clearly a discovery/introspection tool, though it never names the sibling atena_decide to sharpen 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?

'agent-use guidance' hints that this is meant to be consulted by an agent, and the enumerate-what-you-get framing implies a discovery step before acting. However, it never explicitly says when to call this versus atena_decide, nor any prerequisite or ordering.

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

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

With no annotations present, the description carries the disclosure burden and does well: it names the decision categories returned and the accompanying rationale/monitoring/decision-rule payload, and explicitly bounds scope away from diagnosis and emergency medicine. It stops short of stating side effects, whether the call is read-only, or latency/cost behavior, which keeps it from a 5.

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 role, then the call conditions, then the return shape and exclusions — a logical progression with no filler sentences. Slightly dense in the condition list, but every clause maps to a genuine trigger.

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?

No output schema exists, so the description correctly spends its budget describing the return values (decision category, rationale, monitoring, decision rule). The main gap is the absence of any input-payload guidance for a tool whose only argument is an untyped object, but scope and exclusions are otherwise complete.

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 takes one payload object whose seven fields (goal, state, person, history, question, response, constraints) the description never addresses — no guidance on what to supply or how to populate them. Reported schema description coverage is 0%, so the description was expected to compensate and does not; the nested field descriptions in the schema do most of the real work.

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 role ('decision-control specialist') and enumerates the exact outputs returned (maintain/progress/reduce/modify/collect_data/refer plus rationale, monitoring, decision rule), so an agent knows precisely what it produces. It distinguishes itself implicitly from the only sibling (atena_capabilities) by being a decision engine rather than a capability listing, though it never names the sibling explicitly.

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?

Explicit call conditions are enumerated (conflicting signals, symptoms affecting training, stimulus-vs-recovery cost, competing goals, limited time/recovery, longitudinal adaptation) plus two clear exclusions: 'Not a diagnostic or emergency-medicine tool' and 'Do not call for simple factual questions with no decision trade-off.' This is textbook when/when-not guidance.

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