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

Annotations already declare readOnlyHint=false and destructiveHint=true; the description builds on this by disclosing the write-tier approval flow (manager approval, from-now-on vs just-once re-ask behavior, card-as-consent). It also adds behavioral guardrails — "Prefer tiny goals; never dump transcripts" — that constrain how the telemetry should be shaped, which annotations cannot express.

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?

The first sentence is front-loaded with the core purpose, and the use-condition follows immediately. The approval paragraph is dense but each clause earns its place — approval tiers, persistence semantics, and card-as-consent are all operationally relevant; it could still be tightened slightly without loss.

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 13-parameter write-tier tool with no output schema, the description covers purpose, actor, timing, approval mechanics, and payload constraints, while the schema covers all parameters at 100%. The only gap is silence on return value or failure behavior, which is minor for a fire-and-forget telemetry upsert, and "first clear ask" is slightly ambiguous.

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 description coverage is 100%, so the baseline is 3 and the schema carries parameter documentation. The description adds only marginal param-related context ("thin telemetry" implies small goal/last_beat payloads, "for THIS operator" scopes cwd/host), but nothing substantive beyond the schema's own detailed field descriptions.

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?

"Emit or update thin session telemetry for THIS operator (host coding agent self-announce)" states a specific verb (emit/update), resource (session telemetry), and scope (THIS operator). It distinguishes itself from the many attention siblings (create_attention_directive, ack_attention_directive, park_attention_sessions) by making the self-announce role explicit and even naming its consumer (voice CoS via list_attention_sessions).

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?

"Use when YOU are Grok or Claude Code at session start / status change" is an explicit trigger condition, and "Call it on the first clear ask; the card is the yes — do not re-ask in chat" gives operational when-to-act guidance. It lacks explicit when-not-to-use phrasing or named alternatives, though the self-announce scoping implicitly excludes the directive-management siblings.

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