evidence_begin

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

With no annotations provided, the description must fully disclose behavior. It adds qualifiers 'sanitized, bounded, local' that hint at safety and scope, but does not explain what these mean in practice (e.g., session lifetime, data handling, side effects like clearing previous state). The agent gets little insight into the tool's actual behavioral traits beyond the vague qualifiers.

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 a single, front-loaded sentence with no redundant wording. It earns its place by stating the core purpose. However, given the complexity of a session-start tool with parameters, a slightly longer description would be acceptable, but as written it is efficiently concise.

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 tool has no annotations, no output schema, and two undocumented parameters. The description is far too sparse to be considered complete for an agent to select and invoke it correctly. It leaves the agent without knowledge of parameter semantics, session behavior, return values, or workflow integration with sibling tools.

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 two parameters (label, metadata) with 0% description coverage, and the tool description does not mention them at all. The description adds no meaning to what these parameters are for, how they affect the session, or their format requirements. This is a critical gap.

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 uses a specific verb ('Begin') and a specific resource ('sanitized, bounded local evidence session'), clearly distinguishing this tool from its siblings (evidence_note, evidence_finish). It conveys the core function of starting an evidence collection session without ambiguity.

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?

No guidance is provided on when to use this tool versus alternatives. There is no mention that it should be called before evidence_note or evidence_finish, nor any context about prerequisites or exclusions. The 'Begin' verb only implies sequencing from the name, not from the description.

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