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

No annotations are provided, and the description does not explicitly disclose whether the tool is read-only or has side effects. Although 'List' and 'Gap report' imply a non-destructive operation, the lack of an explicit statement leaves uncertainty. The description also does not mention any potential side effects or system modifications.

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?

The description is concise and well-structured, with two focused paragraphs. It states the main purpose first, then technical details about soft-joining and the gap report, and closes with a doc reference. No unnecessary fluff or redundant information is present.

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 description mentions a gap report and soft-join logic but does not explain the structure of the output or the exact content of the gap report. While the output schema is noted as present (but not shown here), the description itself lacks details on return format, possible error conditions, or edge cases, leaving some ambiguity for a complex reporting tool.

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 67% (two of three parameters have descriptions). The 'agent' and 'probes' parameters are well-defined in the schema descriptions, but 'limit' lacks a description. The tool description adds some context for probes (live scorecard) but does not clarify limit's semantics beyond the schema's min/max/default.

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 clearly states the tool's primary function with a specific verb and resource: 'List recent working sessions and durable memories by agent.' It also highlights the unique gap report feature, which distinguishes it from sibling listing tools. The purpose is immediately understandable and specific.

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 description provides some implicit usage context (e.g., gap report for protocol misses, undistilled sessions, and author_label issues), but it does not explicitly state when to use this tool over siblings like memory_session_list or memory_recall. No direct comparison or 'use this when' guidance is given.

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