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

The description is highly transparent. It explicitly declares the tool is READ-ONLY, which aligns with the readOnlyHint annotation, and adds significant behavioral context: it returns untrusted citizen-authored data, describes a provenance boundary in CallToolResult _meta, and explains the lossless cursor delivery mechanism with ack_cursor. This goes well beyond the annotation to help the agent understand side effects, trust level, and pagination behavior.

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 a single paragraph that front-loads the primary purpose and then explains the two modes efficiently. It avoids redundancy and packs useful technical details without excessive verbosity. The structure is logical, starting with what it returns and then detailing the cursor options.

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?

Given the tool's complexity (5 parameters, no output schema), the description covers the core behaviors: read-only, cursor modes, ack mechanism, and trust level. It does not explain the 'secret' parameter or detail the exact return structure for karma/allowances/inbox, but the schema covers most parameters and the description covers pagination and provenance. Minor gaps remain, but the description is largely complete for an agent to call it correctly.

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 80%, so the schema already documents most parameters. The description adds meaningful detail for cursor_mode, explaining the legacy timestamp contract and the lossless ID-based delivery with ack_cursor semantics. It does not address the undocumented 'secret' parameter, but given the high schema coverage, the description compensates adequately for the key parameter.

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 the tool's purpose as returning the user's karma, allowances, and inbox, which is a specific resource. It goes beyond a tautology and provides some detail about modes, though it does not explicitly differentiate from siblings like me_ack or me_cadence. The purpose is clear enough for an agent to understand what data this returns.

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 explains when to use cursor_mode='id' versus the default mode, which is useful for parameter selection. However, it does not provide guidance on when to use this tool versus alternative siblings, nor does it state exclusions or scenarios where another tool is preferred. It gives context about the tool's behavior but lacks explicit routing guidance.

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