check_slo_status

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

No annotations are provided, so the description carries the full burden. It discloses the analytical behavior (compliance, error budgets, burn rate, availability vs. latency) and the key input dimensions, which is solid. It stops short of stating whether the operation has side effects or which data source backs it, but the described check is inherently read-only and non-destructive.

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?

The description is compact and front-loaded: one summary line followed by a clear arg list. Every sentence serves a purpose, and the arg list maps directly to parameter names. There is no filler or repeated schema information beyond the valuable defaults and units.

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?

Given the six-parameter schema with zero description coverage and no annotations, the description does a good job of explaining every parameter's role and typical defaults. An output schema exists, so the return shape is covered separately. It lacks only a brief note on when to select this tool over metric/log-querying siblings, but the tool's purpose is sufficiently self-contained.

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 description adds meaningful semantics for most parameters, including units (milliseconds, hours), range(0.0-1.0 for availability, 1-720 for window), and default values. The one gap is latency_percentile: it says 'default p99' while the schema expects a fractional default 0.99, which could lead an agent to pass 99 instead of 0.99. The description doesn't explicitly clarify the 0-1 fraction format.

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 states a specific verb ('Check') and a specific resource ('SLO compliance') and names the measurable aspects: error budgets, burn rate, availability, and latency targets. This clearly distinguishes it from sibling tools like query_prometheus or get_pod_metrics, which address raw data retrieval rather than SLO compliance assessment.

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 purpose is clear enough that an agent can infer when to use it, but the description provides no explicit guidance on when to choose this tool over siblings, nor any exclusions. It does not mention alternatives for cases where raw metrics or log queries are needed instead.

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