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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful context that the output is raw, unsummarized DB rows rather than aggregates, but says nothing about the volume of a full-system dump, pagination, filtering, permissions, or cost — meaningful gaps for a tool that returns broad system state.

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?

Two tight sentences, front-loaded with what the dump contains and ending with the 'no fake numbers' qualifier. Efficient, though the second sentence leans slightly promotional rather than informational.

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 bears some burden for describing return content; it enumerates the entity types returned, which is helpful. However, it omits return format, size/volume expectations, and whether the dump is paginated or bounded, which matters for a whole-system read.

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 and schema description coverage is 100%, so there are no parameter semantics to explain. Baseline 4 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?

States a specific resource and scope ('raw system state dump — actual DB rows for kernels, devices, jobs, evidence, registrations, capabilities, agent conversations, audit log'), which tells an agent precisely what data this returns. It does not, however, name or differentiate itself from the many sibling readers (get_telemetry_logs, get_active_telemetry, get_telemetry_stats, emit_telemetry), so an agent cannot infer routing from the text alone.

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 explicit guidance on when to choose this tool over the sibling telemetry/stats readers, nor any prerequisites or exclusions. The phrase 'No fake numbers, no summaries' only vaguely implies a preference for raw data over summarized tools without naming any alternative.

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