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

Annotations already declare the safe read profile, yet the description adds real context the annotations cannot: PII facts are masked as ••••••, maskedKeys lists which keys were masked, and values are revealable only in the console under audit. That is exactly the kind of access-control caveat an agent needs and cannot get from readOnlyHint.

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?

One front-loaded sentence with the resource stated first, followed by an ordered list of returned components. It is dense but every clause carries information; the masking parenthetical is the only slightly heavy insertion, and it earns its place.

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?

There is no output schema, so the description must carry the return shape, and it does so by enumerating the five provenance components. Combined with the annotations covering safety and the one-input schema, an agent has enough to call it correctly; only the traceId acquisition path is unaddressed.

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?

There is a single parameter and schema coverage is 100%, with 'Trace ID of the execution' already documented in the schema. The description adds no format, sourcing, or acquisition guidance for the traceId (e.g. where to obtain one), so 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?

States a specific verb and resource: 'Get the lineage of a single decision'. The enumerated return contents (why per rule, input facts, responsibility chain, rule snapshot fingerprint) make the scope concrete. It does not name the nearest siblings (e.g. lexq_history_get, lexq_logs_get), so differentiation is left implicit, keeping it below a 5.

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 phrase 'a single decision' plus the required traceId implies this is the per-execution drill-down rather than the list/aggregate tools, but it never says so explicitly. No when-not-to-use condition or alternative is offered, so the agent must infer routing from the sibling names alone.

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