get_intervention_evidence

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

With no annotations provided, the description carries the full behavioral burden and does so well: it states the tool is strictly read-only, writes/signs/executes nothing, requires three environment settings, takes tenant only from configuration, and returns OK, REFUSED, or UNAVAILABLE rather than made-up data. It also discloses an API-version dependency and failure semantics.

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 front-loaded with purpose and then layers in read-only behavior, environment requirements, return statuses, version dependency, and scope disclaimer. It is slightly long and repeats 'records you supply,' but most sentences add concrete value.

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?

An output schema exists, so return-value explanation is not strictly needed, yet the description still usefully names the possible statuses. However, for a tool with a nested, undocumented request parameter, the definition stops short of explaining the input shape an agent needs in order to call it correctly.

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 description coverage is 0%, and the single required parameter is a nested object with additionalProperties. The description only says evidence comes 'from the records you supply' and that tenant is never an argument; it does not describe the request object's fields or structure, leaving the parameter materially undocumented.

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 gives a specific verb+resource: it retrieves evidence for whether an intervention took effect, from supplied records. It does not explicitly distinguish itself from close siblings such as get_receipt_evidence or get_decision_evidence, so the agent must infer which evidence-retrieval tool to use.

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?

Usage context is implied through 'records you supply' and the disclaimer that 'a mapping or readout is not a compliance finding,' but there is no explicit when-to-use guidance versus alternatives. The agent is left to infer selection among get_decision_evidence, get_receipt_evidence, and similar siblings.

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