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

Annotations already declare readOnlyHint=true, but the description adds critical behavioral context beyond that: it states that numbers come from a real discrete-event simulation, mandates quoting them verbatim (anti-fabrication), warns against rounding or computing derived figures from training-data recall, and advises re-calling for follow-ups. It also discloses a simulation duration limit (30 days) and directs users for longer studies. This significantly exceeds annotation coverage.

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 appropriately sized—not too long—and front-loaded with the core action. Every sentence adds value: purpose, required inputs, optional inputs, output summary, usage guidance, alternative-tool guidance, and a critical anti-fabrication directive. There is no filler or redundancy.

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?

Considering the tool's complexity (7 parameters, optional distributions, output summary, and multiple sibling tools), the description covers all necessary aspects: what it does, parameter meaning, output shape, when to use it, and behavioral constraints. The output schema is present, and the description doesn't need to explain return values in detail. The anti-fabrication and simulation-time limits round out a complete picture.

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 schema has 100% parameter description coverage with detailed descriptions, including units and ranges. The description restates the key params (λ, μ, c) and mentions optional ones, but it does not add substantive meaning beyond what the schema already provides. Baseline of 3 is appropriate given the schema's completeness.

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 opens with a specific verb and resource: 'Run a generic M/M/c queue simulation.' It clearly lists required inputs (arrival rate, service rate, server count) and outputs, and explicitly distinguishes itself from siblings by calling itself 'the primary tool' for staffing/average-wait questions and preferred over simulate_scenario for flat-number what-if questions.

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 description provides explicit when-to-use guidance: it is the primary tool for 'how many servers do I need?' and 'what's my average wait?' questions, and it names an alternative (simulate_scenario) with a clear rule for when to prefer this tool instead. It also instructs to pull peak params from describe_scenario, giving concrete usage context.

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