Recent activity count

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

Annotations already establish read-only, idempotent, non-destructive, open-world behavior. The description adds a trait the annotations do not: the value is cached for speed, signaling potential staleness, which is genuinely useful for an agent deciding whether to trust the figure.

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?

Four short labeled sections, purpose front-loaded, every sentence carrying distinct information. The bold-header formatting is slightly heavier than needed for such a small tool but nothing is wasted.

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 steps in to say the return is a single count, and it covers the no-parameter invocation fully. The one remaining gap is that 'recently' has no defined time window or freshness guarantee, which matters for interpreting a cached number.

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?

The tool takes zero parameters, so the baseline is 4; there is no argument surface to misdocument. The description correctly notes it returns one count rather than a dimensioned result.

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 names a specific output — a single cached count of recent project activity — and explicitly contrasts it with tools that produce breakdowns. It is distinguishable from siblings like get_activity_stats, get_event_stats, and get_analytics_timeseries via the 'no dimensions to slice' framing, though it never names those siblings directly.

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 an explicit 'Use when' (a cheap check of whether anything is happening before deciding what to investigate) and a 'Not for' exclusion (anything requiring breakdown). Clear routing context, but no named alternative tool for when a breakdown is actually needed.

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