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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety/behavior profile is covered. The description adds some value beyond that (always-33 kernel behavior, slotignored slots drop out, returns a 'stamped re-ground'), but it stays in unexplained jargon and never clarifies return shape or side effects of the stamp.

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 core action and reasonably compact across two sentences. The trailing 'Built for Grok, by request' is pure fluff that does not help an agent select or invoke the tool, costing it a perfect score.

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 read-only, idempotent tool with fully documented parameters and no output schema, the description covers the essential mechanics (re-score, drift reporting, stamped result). The main omission is disambiguation from overlapping siblings, but that is a routing rather than a calling gap.

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 'content', 'baseline' and 'verbatim' are already fully documented in the schema. The description's mention of 'drift vs an optional baseline score' echoes the baseline parameter but adds no syntax, format, or behavioral detail beyond what the schema provides — the 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 ('re-ground') on a specific resource ('.faf content') and enumerates what it does: re-scores with the faf-kernel, reports drift vs an optional baseline, returns a stamped re-ground. However, it does not name or differentiate itself from near-neighbor siblings like delta_check or faf_score, which also concern scoring/drift, so the agent must infer the boundary.

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 explicit re-grounding primitive for long sessions: drift → refresh → re-grounded' gives an implied when-to-use context (long sessions, drift scenarios). But it never names an alternative or states when NOT to use it, even though delta_check (drift) and faf_score (scoring) clearly overlap — the routing decision is left to the agent.

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