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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the bar is lower. The description nonetheless adds real context: results are aggregate-only, counts are requests rather than unique agents, and no raw queries, IPs, user agents or geography are exposed, plus provenance/health are kept separate. It stops short of describing freshness or the shape of the aggregates.

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?

Three tight sentences with the resource list front-loaded before the disclosure caveats. Every clause carries information; only the final privacy enumeration runs slightly long relative to the rest.

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?

No output schema exists, so the description must convey what comes back, and it does identify the content categories plus what is deliberately excluded (raw queries, IPs, per-agent identities). It leaves the response structure and aggregation granularity unspecified, which is a minor gap for a read-only stats endpoint.

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 50%: 'period' is documented as activity-only, while 'scope' has no schema description. The description partially compensates by naming the three data domains that the scope values select, but it never explains the default 'overview' scope or how 'period' interacts with non-activity scopes.

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?

States a specific verb (return) and concrete resources: the Agentic Index, MCP/A2A endpoint observations, and machine request counts. A reader knows exactly what data is served, and the tool is clearly distinguishable from the casino-oriented siblings, though the description never names those siblings or contrasts with them.

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?

Usage is only implied: the description enumerates the three data domains, which loosely maps to the scope enum, but it never states when to pick each scope or when to reach for a sibling tool instead. An agent must infer that 'catalog/endpoints/activity' correspond to the non-default scopes and that 'overview' is a summary.

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