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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds useful context beyond that: the output shape ('markdown text plus JSON') and the existence of an optional codex crystallization path. It does not disclose that crystallization writes a linked memory record, which is a meaningful side effect worth flagging given the readOnly annotation.

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 front-loaded sentence with no filler; the action and inputs come first. It is slightly dense with domain jargon ('typed', 'codex crystallization') that a new agent may not parse, but nothing is wasted.

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?

With no output schema, the description does partly cover the return format, which is the right instinct. It still leaves unclear what a 'checkpoint' contains, how turns and checkpoint are merged, and what the crystallization side effect entails, so a 3-parameter synthesis tool is only adequately covered.

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 'n', 'session_id' and 'crystallize' are already documented in the schema. The description only loosely maps its phrases ('typed session-log turns', 'latest checkpoint', 'codex crystallization') onto those parameters and adds no format or default details beyond them.

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 ('Compose a digest') and a specific resource ('typed session-log turns and the latest checkpoint'), which distinguishes it from plain retrieval siblings such as session.recall or session.replay. It does not explicitly name any sibling it replaces, so differentiation is inferred rather than stated.

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?

No guidance on when to choose this over session.checkpoint, session.replay, session.recall, or memory.aggregate. The agent must guess that a digest is a synthesis step rather than a read, and nothing says when not to call it.

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