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

Annotations cover safety (readOnly/idempotent/non-destructive), and the description adds genuinely new traits: references are identity-isolated and expiring, and an expired reference is not silently refreshed. It also discloses presentation behavior (structured evidence, no widget) which annotations do not convey.

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?

Front-loaded with the trigger sentence, then clearly labeled Selection/Presentation/Evidence blocks that each earn their place. It is somewhat dense and longer than strictly necessary, with mild overlap between the intro and the Selection block, but 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?

An output schema exists so return shapes need not be spelled out, yet the description still characterizes object/array/scalar evidence results and the expiry model — covering everything an agent needs to call this correctly and interpret it, including the failure mode of stale references.

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%, so the baseline is 3; the description still adds strategy-level meaning — that path targets a section rather than root enumeration, that limit/offset page already-captured arrays rather than fetching upstream history, and that next_offset should be followed. It stops short of adding format examples beyond what the schema already supplies.

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 precise verb+resource: retrieving one specific section or value from evidence already returned by another Research tool. It also names the boundary against near-siblings implicitly (refreshing data, raw API access, other widgets), so an agent can distinguish it without reading the schema.

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?

Explicit 'use this when' plus a detailed 'do not use for' list covering refresh, selection changes, enumeration, preview-of-facts, and widget opening. It also gives procedural guidance (use evidence.id + JSON-pointer, request bounded arrays, follow next_offset) instead of leaving it to inference.

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