memory_at

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It conveys that this is a read operation and that ref selects a point in time, but says nothing about how kind filters results, how limit truncates, ordering behavior, or what happens when a ref does not exist. The core behavior is clear but the operational detail is thin.

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 sentences with no waste. The core concept ('Time travel') is front-loaded, the mechanism ('AS OF a specific commit SHA, tag or branch') follows immediately, and the usage hint closes it out. Every word earns its place.

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?

Despite the presence of an output schema covering return values, the definition leaves two of three parameters (kind, limit) unexplained, and misses edge-case behavior for invalid or empty refs. For a moderately complex time-travel tool with filtering and limiting controls, this is a meaningful completeness gap.

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 compensate for all three parameters. It effectively explains 'ref' by naming the accepted value types (commit SHA, tag, branch), but 'kind' and 'limit' receive zero explanation in the description and their semantics are not guessable from the schema beyond their names. One of three parameters documented is insufficient compensation.

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 states a specific verb ('read') and resource ('crew memory AS OF a specific commit SHA, tag or branch'), pairing it with an evocative 'time travel' metaphor that immediately distinguishes it from current-state siblings like recall, list_recent, and search_memory. An agent can clearly tell this reads historical memory at a point in time.

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 'Great for "what did we know back then"' line gives a clear triggering scenario for when an agent should reach for this tool. It does not explicitly name alternatives or state when not to use it, but the historical-versus-current framing strongly implies the boundary against list_recent and get_memory.

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