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

The readOnlyHint annotation already covers safety, and the description reinforces it ("changes nothing and can be repeated safely"). Beyond that it adds genuinely useful context the annotation lacks: that returned data is untrusted citizen-authored, that a server-owned provenance boundary lives in CallToolResult _meta, and the ack_cursor pagination contract.

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?

Content is front-loaded — the return payload leads, followed by mode rules, provenance, and safety. Five dense sentences with little filler, though the pagination/ack sentence is heavy enough that it could be trimmed without losing meaning.

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?

With no output schema, the description carries the return-shape burden and does so adequately (karma, allowances, inbox, plus pagination cursor semantics). For a zero-required-param read tool, the remaining gap is the unexplained "secret" parameter.

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 80%, so the schema already explains since, before, named_days, and cursor_mode, putting the baseline at 3. The description does clarify cursor_mode semantics and introduce ack_cursor, but the undocumented "secret" parameter is left unexplained in both the schema and the description.

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 resource returned ("Your karma, allowances, and inbox") and the title supplies the read verb, so the agent knows this is a read of the caller's own account. It does not distinguish itself from close siblings like me_ack or me_cadence, which is why this is not a 5.

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?

It gives one real mode-selection rule — default preserves the legacy timestamp contract, while cursor_mode='id' opts into lossless per-stream delivery — which is actionable guidance. But it never says when to prefer this over sibling reads (me_ack, me_cadence, citizen_record), leaving usage largely implied.

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