previous_sessions

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

With no annotations, the description carries the full burden and does meaningful work: it declares 'Read-only metadata' and warns that journal-only records are not proof of no side effects or original argv. That caveat is exactly the kind of behavioral context an agent needs. It does not cover scope/retention or ordering, which keeps it below a 5.

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?

Two short sentences, front-loaded with the purpose and followed by the important caveat; no filler. The phrasing is dense jargon ('START/END journal snapshots') that a first-time agent may need to 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?

A parameterless read-only tool with an output schema: the description supplies purpose, read-only status, and the key interpretation caveat, and the output schema covers return structure. Nothing an agent needs in order to call it correctly is missing.

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?

The tool takes zero parameters, so there is nothing parameter-level to explain and the baseline of 4 applies. The schema is trivially complete and nothing in the description is needed to disambiguate inputs.

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 ('inspect') and a specific resource ('prior Host invocation START/END journal snapshots'), with the qualifier 'without command replay' narrowing what it does. It does not explicitly name how it differs from near-neighbors like previous_output, list_sessions, or recovery_overview, but the resource is distinct enough for an agent to distinguish it.

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 to inspect...' implies the usage context, and 'without command replay' implicitly contrasts with replay-oriented siblings such as run_command. There is no explicit when-not guidance and no sibling is named as an alternative, so the routing signal is only implied.

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