Get Handed-Off Evidence

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuinely behavioral fact beyond that: the returned evidence is access-scoped to what was handed off to the caller. It does not say what happens if nothing was handed off or whether content vs. metadata is returned.

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 short, front-loaded sentence with no filler, and the role tag leads. It is arguably over-terse for the job it needs to do, but there is no wasted verbiage.

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 one-parameter, read-only fetch with full annotation coverage, the definition is close to viable, but with no output schema the description should at least hint at the return shape (single evidence item vs. collection, artifact content vs. reference). The relationship between task_id and the handed-off evidence is also left unexplained.

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 100% and there is only one parameter (task_id, required), so the schema carries the load and the baseline is 3. The description adds no meaning about whether task_id is the task the evidence belongs to or a separate handoff identifier, which is a real ambiguity given the 'handed off to you' scoping.

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?

States a specific verb (get) and resource (evidence) with a clear scope qualifier: only evidence 'handed off to you.' The [ANALYST/BUILDER/REVIEWER] tag signals the caller role. It is distinguishable from submit_evidence/handoff_evidence by the 'handed off to you' framing, though it never names a sibling explicitly.

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?

Usage is implied by the phrase 'handed off to you' – the agent should call this after a handoff has occurred – but there is no explicit when/when-not, no prerequisites, and no routing against near siblings like review_evidence or get_task_detail. Adequate but leaves the agent to infer the trigger condition.

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