retrieve_evidence

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

With no annotations, the description must carry the behavioral disclosure burden. It adds useful behavior-related details about retrieval modes ('hybrid', 'lexical', 'vector') and scoping via tenant_id and source_type. However, it does not explicitly state the operation is read-only, mention auth requirements, or disclose rate limits or side effects, so it is adequate but not comprehensive.

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 compact and well structured: a one-sentence purpose statement followed by a scannable parameter list. Every line adds useful information and there is 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?

Given the tool's complexitycars, an output schema exists and parameter semantics are fully documented, so the calling contract is largely complete. The main gap is the absence of guidance on how this tool relates to closely named siblings, but that issue is already reflected in the usage_guidelines score and does not prevent a competent agent from invoking the tool 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?

The input schema has 0% description coverage, so the description must compensate, and it does thoroughly. All six parameters are explained beyond their bare property names: mode's strategies are expanded, tenant_id is described as scoping search to tenant data, trace_id is tied to audit tracing, source_type gets examples, and top_k is described as returning ranked chunks. This is strong parameter documentation.

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 clear action and resource: 'Execute evidence retrieval across indexed content.' However, the sibling set includes get_evidence and explain_retrieval, and the description does not explain how this tool differs from them, so it is clear but lacks sibling differentiation.

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 guidance on when to use retrieve_evidence versus get_evidence, get_document, or explain_retrieval. It only describes the tool's own operation and parameters, with no context about exclusions, prerequisites, or alternative conditions.

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