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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, but the description adds substantive behaviour beyond them: no cell values are returned, no Oracle call is made, the trail draws on Activity plus the remembered-results fingerprint, and embedded trail text is treated as data rather than instructions. Those facts materially change how an agent should interpret and trust the output.

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?

It is compact with no filler and each sentence adds a new fact (purpose, mechanism, permissions, guarantees, safety). It is slightly front-loaded against the agent's need, since the actual routing cue ('Use it to check where an answer came from') sits last rather than first.

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?

With no output schema, the description must describe the return payload, and it does so by enumerating the trail components. Combined with the access rules and the explicit 'no cell values' caveat, an agent has everything needed to call this and interpret the result correctly.

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 the single param already documents the 16-character hex pattern, so the schema carries the burden. The description adds only marginal meaning by tying the Ref to 'a numeric answer', without explaining format, provenance rules, or failure behaviour for malformed refs; baseline 3 applies.

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 opens with a specific verb and resource: 'Reads the source trail for a Ref from a numeric answer', then enumerates exactly what the trail contains (definitions, exact members, point of view, connection, application, cube, read time, checked data status). This is clearly distinct from siblings like explain_variance or remembered_results without needing to name them.

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?

It gives an explicit positive use case ('Use it to check where an answer came from') and states applicability by role (members read their own records, org admins read the organization's). It does not name any alternative sibling or state when not to use it, so it falls short of the full 5.

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