get_evidence

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds that the reference must be 'known' and resolved 'after discovery', which is useful, but it does not disclose behavior such as unknown-reference errors, access requirements, or what the resolved output contains.

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?

A single sentence that is front-loaded with the core operation and devotes the rest to the essential calling detail: separate ref_type and ref_id after discovery. Every clause earns its place and there is no filler.

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 only two required parameters, an enum in the schema, and an output schema, the call itself is fairly complete. Yet with dozens of sibling get_* tools, the absence of any guidance about when the generic resolver is appropriate versus the specific typed accessors leaves a meaningful selection gap.

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 coverage is only 50%: ref_id is documented, but ref_type is exposed only as an enum without explanation. The description adds the important relationship that ref_type and ref_id are paired and must be passed separately, but it does not clarify what each ref_type value represents or how the reference was obtained during discovery.

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 specific operation ('Resolve a known typed reference') and the key requirement that ref_type and ref_id are passed separately. It is clear that this retrieves an existing referenced evidence object, though it does not explicitly distinguish itself from the many sibling get_* tools or define what 'evidence' means.

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?

'after discovery' provides a useful usage context: this tool is for resolving references that are already known from a prior discovery step. However, it does not state when to prefer this generic resolver over alternatives like get_artifact or get_run, nor does it give explicit exclusions.

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