usage_stats

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

With no annotations provided, the description carries the full burden and does so excellently. It discloses key behavioral traits: the counting unit (tool calls, not sessions/people), the multi-line logging per session, the reset behavior on redeploy, and the limitation as a rough activity signal. This is exactly the kind of context an agent needs to interpret results correctly.

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 efficiently structured: it leads with the primary purpose, then adds essential behavioral caveats, then documents the argument. Every sentence contributes meaningful information—no fluff or redundancy—and the Args section is clean and minimal.

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?

This simple 1-parameter tool is fully covered: purpose, counting semantics, reset limitations, and parameter meaning are all explained. The presence of an output schema means return-value documentation isn't the description's job. Nothing relevant is missing for an agent to invoke and interpret this tool 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?

The schema only provides the parameter type, title, and default for 'days_recent' with no description. The tool description adds semantic meaning by explaining it is the 'Size of the recent window in days', which clarifies that it defines a lookback period rather than a specific date. This goes beyond the raw schema.

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 opens with a specific verb and resource ('Show how much this MCP server has been used'), clearly stating the tool's function. This is distinct from the sibling data-retrieval tools, which fetch external datasets, so the purpose 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?

Provides meaningful usage context: it explains that the tool counts tool calls rather than people, warns about resets on redeploy, and positions the local counter as a substitute for unavailable per-connector usage. This gives the agent clear situational framing, though it doesn't explicitly contrast with an alternative tool (none exists).

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