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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description's added value is 'Keyless' (no auth/credential needed) plus what the aggregate actually measures; it stops short of describing aggregation granularity or whether counts are current/period-bound, which matters for a statistics tool.

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?

Front-loaded with the aggregate scope, then use cases, then examples – a sensible order with no filler sentences. Slight redundancy: the state option is described in prose, again in the example questions, and again in the invocation examples.

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?

For a one-optional-param aggregate tool with no output schema, the description covers what is counted and how to filter, which is enough to invoke it correctly. It would be stronger if it sketched the response fields (count fields, participant totals) or noted that counts are not per-plan records.

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?

With one optional parameter at 100% schema coverage the baseline is 3, and the description adds meaning on top: it frames the parameter as an optional restriction to 'one US state' and demonstrates it with a concrete call ({ state: "TX" }). Small but real value beyond the 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?

States a specific verb+resource ('aggregate counts across PBGC's registers') and enumerates exactly what is counted: trusteed plans, participants affected, and premium-paying plans split by single- vs multiemployer. It is clearly distinguishable in substance from the pbgc_search_* siblings, but it never names them, so sibling differentiation is implicit rather than explicit.

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?

The quoted example questions ('how many pension plans has PBGC taken over', 'PBGC trusteeships in Texas') give an agent concrete situations that select this tool, and the state filter's condition is stated. What's missing is an explicit exclusion, e.g. 'for details on individual plans use pbgc_search_trusteed_plans'.

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