latency_budget

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description earns some credit by confirming the tool does no external lookups ("pure arithmetic" / "caller-supplied"), which reassures the agent results are deterministic and offline. It omits anything about the 30-hop cap, how parallelGroup affects the arithmetic, or what a hop 'share' actually means.

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 sentences, zero filler, with the core action front-loaded and the execution model (pure arithmetic) as a compact qualifier. Nothing here is restated from annotations or schema.

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 values need not be described. But for a tool whose whole value depends on interpreting hop fields correctly, the description leaves parallelGroup and cacheable unexplained and gives no hint about how the percentile choice affects the split. Adequate to identify the tool, not adequate to invoke it optimally.

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 description coverage is 0%, so the description carries the full burden, yet it explains none of targetMs, percentile, or the hop fields. Critically, cacheable and parallelGroup are semantics-bearing fields whose effect on the budget split is completely undocumented, and an agent cannot guess how caching discounts a hop's share.

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 and resource ("split an end-to-end latency objective across hops") plus the secondary output ("show which hops exceed their share"). The line "Pure arithmetic over caller-supplied estimates" sharply distinguishes it from data-fetching siblings, but it never names the closest alternative, slo_budget, so the boundary is left for the agent to infer.

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 phrase "caller-supplied estimates" implies the precondition that the agent must already have per-hop numbers, and that this is an analysis step rather than a measurement step. However there is no explicit when-to-use, no when-not-to-use, and no routing to slo_budget or capacity_plan, which is the most likely confusion point.

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