cos_situation_detect

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

With no annotations provided, the description must carry the full behavioral burden. It discloses the null output behavior and the override of persona primary_formulas, which are useful. However, it does not clarify whether the override is a persistent side effect or an in-memory setting, nor does it mention any permissions, rate limits, or other constraints.

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?

The description is two sentences, efficiently front-loaded with the core action 'Classify'. It lists the categories in parentheses and the override behavior in a second sentence, with no extraneous words. This is an appropriate size for the tool's complexity.

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 description covers the core classification behavior, the possible outputs, and the null case, which is good for a simple tool. It also mentions the override side effect, but leaves the input format unexplained and provides no context on the persona or when to use this tool. Given the output schema exists, the return structure is likely covered, but the description is not fully self-sufficient.

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 schema has a single 'signals' parameter with zero description coverage, so the description must compensate. The description refers to 'a set of signals' and lists the classification categories, which gives some context about the content. However, it does not specify the expected format (e.g., JSON array string) or provide examples, leaving the parameter semantics underdefined.

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 clearly states the tool classifies signals into a specific set of situational dispatch chain IDs and returns null if none match. The verb 'Classify' and the enumerated categories make the purpose unambiguous. It also distinguishes itself by mentioning the override of persona primary_formulas, which sets it apart from generic classification siblings.

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?

The description provides no explicit guidance on when to use this tool over others. It says what the tool does but does not mention alternatives, prerequisites, or conditions for invocation. The only implicit hint is that it is used when there are signals to classify, but it lacks the explicit 'when to use vs. when not to use' guidance.

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