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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is fully covered without description help. The description adds the useful scoping fact that results belong to exactly one session and the caution that this is not conversational memory. It says nothing about ordering of "recent" actions, truncation behavior, or what a summary entry contains beyond what the output schema presumably supplies.

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?

Three short sentences, front-loaded with what is read, then when to use it, then the exclusion. There is minor overlap between "belonging only to one ai_session_id" and the later negative framing, but no filler sentences.

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?

The tool is simple (one required param), has an output schema so return shape needs no explanation, and the description covers purpose, use cases, and a hard prohibition. The remaining gap is sibling routing: it never tells the agent which tool to use instead when the goal is cross-session or conversational recall.

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%: limit is fully documented in the schema (default 10, max 20) but ai_session_id has no schema description. The description partially compensates by stating that returned actions belong only to one ai_session_id, implying it is a strict scoping key rather than an optional filter. It adds no format or provenance detail for the id itself.

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 uses a specific verb plus resource ("Reads recent tool-action summaries") and constrains scope to a single ai_session_id, which already separates it from session-wide tools. It also explicitly excludes conversational-memory use. It stops short of naming the closest sibling alternatives (e.g. get_recent_tool_calls, agent_history), so the differentiation is conceptual rather than 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?

"Use this for execution recovery, debugging, or audit" gives concrete when-to-use conditions, and the following sentence gives a clear when-not-to (inferring chat topic or project mainline). No sibling tool is named as an alternative, so an agent still has to infer which other tool to pick for a broader retrospective view.

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