get_evidence

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

With no annotations provided, the description carries the full burden. The verb 'Retrieve' implies a safe read operation, and listing the returned components adds context. However, it does not explicitly confirm read-only behavior, error scenarios, or any side effects, leaving some transparency gaps.

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 extremely concise: a single clear sentence followed by a brief Args section. Every word earns its place, and there is no redundant information.

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?

For a simple one-parameter get-by-ID tool, the description covers purpose, the parameter, and the nature of the returned data. An output schema exists to fully define return structure. Missing only explicit usage guidance, which prevents a perfect score.

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 only declares evidence_id as a string with no description. The tool description adds that it is a 'UUID string of the evidence record', giving the parameter real semantic meaning beyond type and name.

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 the specific verb 'Retrieve' followed by a precise list of returned content (raw source evidence snippet, timestamps, video association, confidence). This clearly distinguishes it from sibling tools like get_source and get_knowledge, which presumably retrieve different resources.

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 implies usage: this tool fetches a specific evidence record by its ID. However, it provides no explicit guidance on when to use this tool versus alternatives (e.g., search_sources or get_source), nor any exclusions or prerequisites beyond the required evidence_id.

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