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 adds that this is a pure analytical calculation based on named queueing models, which helps set expectations for deterministic output. However, it says nothing about validity conditions (e.g. that arrival rate times service time must be below capacity, or how an unstable/overloaded queue is reported) — a meaningful omission for a sizing calculator.

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 dense sentence that front-loads the core action and then enumerates the returned metrics. No filler and appropriately sized for a calculator tool, though the clause list is slightly run-on.

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 no explanation, and annotations cover the safety profile. But with six required, zero-documented parameters and no statement of the model's preconditions or interpretation of results (e.g. what a wait probability near 1 implies), the definition is only marginally sufficient for correct invocation.

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% for six required parameters, so the description must carry the explanatory burden and it does not. It never clarifies units (serviceTimeMs is implied by the name), what maxConcurrencyPerConsumer actually means, or how backlogMessages interacts with drain-time output. The output list loosely maps to targetUtilizationPercent and backlogMessages, but several parameters remain semantically opaque.

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 and resource ('Size consumers for a queue') and the modeling technique (Little's law, Erlang C), so an agent knows exactly what computation this performs. It also enumerates the computed outputs (utilization, wait probability, backlog drain time, consumers needed), which is more specific than most siblings. It does not explicitly contrast itself with capacity_plan or slo_budget, keeping it at a 4.

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 listed inputs and outputs (arrivals, service time, backlog, target utilization) sketch the scenario where the tool applies, but there is no explicit 'use this when' statement, no exclusions, and no mention of capacity_plan or latency_budget as alternatives. An agent can infer the context but must guess at boundaries.

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