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

Annotations already declare readOnly, idempotent and non-destructive behavior. The description adds genuinely useful framing beyond that — these are provisional notes that never override approved canon — but says nothing about return shape, freshness, or how provisional notes are populated/expire.

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?

Three tight sentences, front-loaded with the core purpose and no filler. Slight cost: the pagination note is appended after the canon caveat rather than grouped with retrieval semantics.

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 rich annotations and an output schema present, the description only needs the non-obvious facts, and it delivers the key ones (provisional nature, canon precedence, paging). It is complete enough to call correctly, though the required projectId is left unqualified.

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%, so the description must carry the parameter burden. It does explain offset as the mechanism for reaching older checkpoints, but projectId (the required parameter) gets no explanation of scope at all.

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 and resource ('Retrieve provisional story handoffs to recover progress across chats') and implicitly separates itself from canon tools via 'never override approved canon'. It doesn't name a sibling outright (e.g. get_canon_history or search_story_canon), so 4 rather than 5.

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?

Gives one concrete usage instruction — use offset to page to older checkpoints — and hints at scope via the canon caveat. It never states when to prefer this over sibling tools like get_continuity_context or get_canon_history, so guidance is implied rather than explicit.

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