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 the safety profile is covered. The description contributes the useful fact that the envelope is "content-free," meaning no conversation content is persisted, but it never says what record is created, whether repeated calls at the same boundary merge, or how the nine boundary states differ in effect.

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 short, front-loaded clause with no filler or redundancy. Its brevity is achieved by omission rather than by tightening, but structurally it is clean and readable.

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 write tool with a nine-value enum, three required and three optional identifier parameters, zero schema descriptions, and no output schema, the definition is far too thin. An agent cannot tell which boundary to emit, what next_session_id and parent_session_id are for, or what a successful write produces.

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 largely fails it. "Content-free" hints that no content fields exist, but boundary (a nine-value enum including clear, compact, compress, rewound), session_id vs next_session_id vs parent_session_id, and reason are all left unexplained.

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 names a lifecycle-hook role and a write action ("write a ... capture_session envelope"), so the general purpose is inferable. However, "capture_session envelope" is internal jargon that is never defined, and nothing distinguishes this from siblings like memory_capture_turn or memory_turn_context.

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?

There is no statement of when to call this versus the many memory_capture_* / memory_turn_* siblings, and no guidance on which boundary value corresponds to which situation. The word "hook" weakly implies automatic invocation at lifecycle events, but that is inference, not guidance.

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