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

No annotations exist, so the description carries the full burden. It does disclose the default selection semantics and the shape of what comes back, implying a read-only operation. But it says nothing about what happens when no prior session exists, whether reading a brief marks it as consumed, or any permission constraints.

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 sentence, front-loaded with the verb and resource, then default behavior, then purpose. Every clause contributes distinct information; nothing is padded or redundant.

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 usefully enumerates the returned fields (goal, files touched, recent turns), which is the key compensatory detail. Minor gap: no guidance on empty-result behavior for a tool whose entire premise depends on a prior session existing.

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 the schema already explains platform, max_chars and session_id in detail. The description's 'by default the latest one from a different harness' simply restates what the session_id/platform descriptions already say, adding no new syntactic or format guidance. Baseline 3 applies.

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?

A specific verb ('Load') plus a well-defined resource ('compact handoff brief') with its contents enumerated (goal, files touched, recent turns) and a stated default selection rule. It never names its nearest siblings (drive_recall, drive_context, drive_sessions), so the agent must open those schemas to know which retrieval tool to pick.

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?

The clause 'so you can continue that work' clearly frames the scenario: resuming interrupted work from another harness. The default ('the latest one from a different harness') tells the agent it can call with zero arguments. However, it gives no exclusions or alternatives — nothing says when to use drive_recall or drive_context instead.

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