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 still adds real context beyond them: the snapshot is immutable, the evidence catalog excludes source bodies, and the read does not authorize execution — a non-obvious boundary for an agent that might assume reading context grants execution rights.

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?

Two tight sentences: the positive scope first, the negative boundaries second. No filler and nothing buried.

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?

No output schema exists, and the description sketches the return only qualitatively ('evidence catalog without source bodies'). Combined with an opaque nested-object parameter, an agent still lacks the handoff's provenance and shape, which is a real gap even though the safety semantics are complete.

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 0% and the single parameter is an untyped nested object with no declared properties, so the description carries the burden. It identifies what the object is ('the ResearchContext snapshot carried by a ResearchPilot handoff') but never says how an agent obtains that handoff or what keys it contains, so compensation is partial.

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 (read) and resource (immutable ResearchContext snapshot from a handoff) plus scope ('evidence catalog without source bodies'). This implicitly separates it from researchpilot_read_handoff_evidence (which presumably returns bodies), but neither that sibling nor researchpilot_handoff_summary is named, so discrimination is left to inference.

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 defines what the tool will not do ('does not mutate Studio state or authorize execution'), which implies when it is safe to call, but it gives no positive trigger condition and does not say when to prefer researchpilot_handoff_summary or researchpilot_read_handoff_evidence.

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