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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds the useful note that the result mixes per-notebook counts with the user's overall streak, which is behavior beyond the schema. It does not clarify aggregation semantics when no notebook is given (whether counts are summed) or that idempotentHint=false despite being a read.

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?

A single compact sentence that front-loads the scope ('Per notebook') and then lists metrics with no filler. It is slightly fragmentary — no verb — but every token carries information.

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 an output schema present, the description does not need to explain return shapes, yet it still names the key metrics so the agent can judge relevance. Annotations cover the read-only profile. Only the unstated aggregation behavior when notebook_id is omitted leaves a small gap.

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 100% and the single parameter's description already explains 'omit for every notebook.' The description's 'Per notebook' framing echoes that but adds no new meaning, so the baseline 3 applies.

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 enumerates exactly what is returned — word counts broken down by state (due today, new, mastered, struggling, starred, hard to spell) plus the user's streak — so an agent can tell this is a read-only statistics tool distinct from the word-level siblings. It is a list of metrics rather than a verb+resource statement, but the resource (notebook statistics) is unambiguous.

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?

There is no explicit when-to-use, no exclusion, and no mention of alternatives such as get_due_words or list_words, which surface overlapping data. The agent must infer from the metric list alone that this is the aggregate/summary tool rather than a listing tool.

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