getUsageSnapshot

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

With no annotations, the description carries the full disclosure burden. 'Return' weakly implies a read-only operation, and enumerating the metrics tells the agent what kind of data comes back, but it says nothing about snapshot freshness, cost, permissions, or whether 'current' means pre-aggregated versus computed live — the main behavioral unknown for a telemetry 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?

One sentence, front-loaded with the verb and resource, followed by a compact enumeration of the returned metrics. Nothing is redundant or padded.

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?

An output schema exists, so return shapes need not be spelled out, and the description still names the key metrics. What's missing is only the relationship to similarly-scoped siblings (getCapacity) and any note on snapshot recency, which is a modest gap for a read-only telemetry tool.

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 'window' parameter is fully documented with its enum and default ('today'), so the baseline is 3. The description adds no meaning about how window affects aggregation or which window the metrics default to, so it neither compensates nor detracts.

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 resource ('current usage snapshot') and enumerates the exact metrics returned (events written, recalls, embed-cache hit rate, recall latency percentiles). It does not, however, distinguish itself from the closely related sibling getCapacity, which an agent could easily confuse with a usage/telemetry call.

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 enumerated metrics suggest 'call this to read telemetry', but there is no explicit when-to-use statement, no exclusion, and no pointer to alternatives such as getCapacity or idleStatus. The agent must infer the choice from the metric list alone.

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