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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds genuine context beyond that: there must be a *pending* turn to close, implying an ordered state transition, and "one canonical" envelope implies dedupe/upsert semantics consistent with the idempotent hint. It still omits failure behavior when no pending turn exists and whether it is safe to call multiple times.

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?

A single short sentence with the trigger context front-loaded, and no filler. It is arguably too terse for a 7-parameter mutation tool, but as prose it is efficient and well ordered.

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 non-read-only, 7-parameter state-transition tool with no output schema, the description is thin. Annotations cover the safety profile, but nothing explains the pending-turn lifecycle, what gets stored, what the required fields should contain, or what the agent observes on success or failure.

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 are 7 parameters with 0% schema description coverage and the description mentions none of them. Names like turn_id, agent_context (enum main/subagent), and parent_session_id carry no explanation anywhere, and the required trio (session_id, assistant_message, platform) is never connected to the stated behavior. The description does not compensate for the coverage gap.

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 gives a specific verb pair ("close the pending turn and store") plus a named payload ("capture_turn envelope"), so the action is identifiable. However, "canonical capture_turn envelope" is internal jargon and does nothing to separate this from siblings like memory_remember, memory_turn_context, or memory_session_boundary, which an agent could easily confuse it with.

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 "Stop hook:" prefix implies the invocation context (end of a turn), which is useful timing guidance. But it names no alternatives, no when-not conditions, and no prerequisite details such as what to do if no turn is pending or whether this should be called alongside memory_session_boundary.

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