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

With no annotations, the description carries the full burden, and it does disclose valuable behavior: it scans all history including L2/L1 summaries, returns summaries plus events with ev ids, and opens the episode around an event. It never states that this is a read-only operation, nor anything about result volume, ordering, or cost of a full-history scan.

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?

Front-loaded with 'Dig deeper' and organized as three semicolon-delimited modes ending in a memorable directive; nearly every clause carries information. It is dense and slightly run-on, but not padded.

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 7-parameter tool with no annotations and no output schema, the three main invocation modes are well covered but the remaining parameters are opaque — an agent cannot tell whether since/until filter by time, what radius measures, or what exclude_imports suppresses. That gap matters for a tool described as scanning 'all history'.

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 coverage is 0%, so the description must compensate, and it does explain query, focus_id (with accepted value formats) and focus_event_id. However, since, until, radius and exclude_imports — four of seven parameters — receive no explanation anywhere, leaving the compensation only partial.

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 breaks the tool into three explicit modes (query scan, focus_id open, focus_event_id episode) with concrete id namespaces (l1:/l2:/crit:/board:/ev), so an agent knows exactly what it retrieves. 'Dig deeper' implies contrast with memory_search, but no sibling is named outright, keeping it short of a 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?

'Use before saying you do not remember' is a clear, actionable trigger, and the per-mode parameter descriptions imply which call to make when. There is no explicit when-not guidance or named alternative (e.g., memory_search for shallow lookups), so it stops at 4.

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