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

With no annotations, the description carries the full burden, and it does disclose two real behavioral traits: results are 'bounded' and the Zero-PII guarantee means no raw prompts or replies are returned. It says nothing about authentication requirements, rate limits, what the summary's fields are, or what the default lookback window is when window_hours is omitted.

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 front-loaded sentence with no filler; the parenthetical privacy note is justified because it prevents misuse. Slight loss for dense internal jargon that displaces plain description, but nothing is redundant.

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-parameter, read-only tool with an optional argument and no output schema, the description is close to sufficient: purpose plus privacy behavior are stated. Still missing is whether the window defaults to something, and what categories of latency/fallback figures are returned, which matters given no output schema exists.

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 window_hours already documents its 1–168 hour range in the schema itself. The description adds no meaning beyond that (no default, no interaction with the fallback computation), 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 names a specific verb ('Reads') and a specific resource ('switchboard latency and fallback summary'), so an agent knows it retrieves aggregated telemetry rather than raw data. It does not differentiate itself from the many sibling query_*_observatory tools, and the heavy jargon ('AO-066', 'Zero-PII Protocol') adds little for an agent unfamiliar with the internal codename.

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 guidance on when to choose this tool over the other observatory tools, nor any stated preconditions, exclusions, or follow-up tools. The only cue is the 'observatory' naming pattern, which the description never leverages explicitly.

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