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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description's phrase "open the pending turn" reads like a state change, which sits in tension with readOnlyHint and leaves the agent unsure whether calling this mutates memory state or is a pure read; "return recall" also never says what recall contains or how large it is.

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 no padding, and the hook trigger is front-loaded. It is concise to the point of under-specification, however, and the "open... and return..." construction compresses two distinct behaviors into one clause without separating them.

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 six-parameter hook with zero schema descriptions and no output schema, the description should explain the required identifiers, the meaning of agent_context, and the shape of the returned recall. It covers none of these, leaving an agent unable to construct a correct call or interpret the result with confidence.

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 0% across six parameters, so the description carries the full burden and adds essentially nothing. It only alludes to "this turn" (turn_id) and "prompt" implicitly; session_id, platform, agent_context (the one enum) and parent_session_id are entirely unexplained in both schema and prose.

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?

"Open the pending turn and return recall for this turn" gives a verb pair (open/return) and a resource (turn context), so the general intent is graspable. But the jargon ("pending turn", "recall") is undefined and nothing distinguishes it from siblings like memory_capture_turn or memory_session_boundary, which plausibly also touch turns.

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?

"Prompt-submitted hook" implies it fires automatically when a prompt arrives, which is a hint of when it runs. There is no guidance on when an agent should call it versus memory_capture_turn or memory_search, no prerequisites (does a session must exist first?), and no statement of what happens if invoked outside a hook flow.

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