kernel_agents_subject_history

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

With no annotations supplied, the description carries the full burden and does declare the safety profile up front ("Read-only") as well as a behavioral trait an agent cannot otherwise know: results are ordered oldest first. It also enumerates the kinds of content returned (who asked, the answer, who decided and through what channel, environment problems open at the time). It does not explain what `limit` does or what an empty/unknown subject yields, which keeps it below 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 sentences, front-loaded with the read-only guarantee and the aggregation scope before the ordering and content details. Every clause conveys distinct information — scope, ordering, returned fields, then the usage rule. The parenthetical example is compressed almost to the point of being cryptic, but nothing is padding.

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 two-parameter read tool with no output schema and no annotations, the description does the heavy lifting: it explains what the call returns and in what order, which the schema cannot. The main remaining gap is `limit` behavior and any notion of result size. Nothing else 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?

Schema coverage is 50%: `subject` is already documented in the schema with both example forms, and the description mainly adds the aggregation rule (querying a parent covers its parts), which is genuine added meaning. The `limit` parameter is undocumented in both schema and description, and the description gives no guidance on reasonable values or default behavior. Baseline 3 fits given the partial coverage.

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 pairs a specific verb ("Read") with a precisely scoped resource: everything asked and decided about an issue and all its parts, oldest first. The parenthetical "`web#2653` covers `web#2653:a-b`…" clarifies the hierarchical aggregation, which is the main thing that could confuse an agent choosing among the many history-adjacent siblings. It stops short of naming a concrete alternative (e.g. kernel_agents_history or kernel_chat_history), so differentiation is strong by scope but not explicit.

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 closing directive "Read it before asking about a subject again" gives a clear precondition for use and implicitly steers the agent away from re-asking questions already answered here. That is real when-to-use guidance rather than inference. No exclusion is stated against sibling history tools, so it is not a full 5.

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