get_evidence

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

No annotations are provided, so the description must fully disclose behavioral traits. It only states the action, without mentioning whether the operation is read-only, what happens if the evidence does not exist, or any authorization requirements. This lack of detail forces an agent to guess.

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 concise with a single sentence. However, the role prefix in brackets is somewhat unconventional and could be considered extraneous. The core information is front-loaded, making it quick to parse.

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 simplicity of the tool (one parameter, no output schema), the description is adequate but leaves gaps. It does not explain what 'handed off to you' means in terms of state or dependencies, and it does not describe the return value or error conditions. For a retrieval tool, additional completeness would be beneficial.

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 100% coverage with a single parameter 'task_id' described as 'Task ID'. The description adds no further context about the format, source, or constraints of the task_id, so it does not provide additional value beyond the schema.

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 identifies the action ('get') and resource ('evidence'), and specifies the context ('handed off to you'), providing a clear purpose. However, the role prefix 'ANALYST/BUILDER/REVIEWER' is slightly ambiguous and does not distinguish this tool from siblings like 'handoff_evidence' or 'review_evidence'.

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 when evidence has been handed off, but it does not explicitly state when to use this tool versus alternatives like 'handoff_evidence', 'submit_evidence', or 'review_evidence'. No guidance on exclusions or prerequisites is provided.

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