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

Annotations already declare readOnly, idempotent, non-destructive and closed-world. The description adds genuinely useful behavioral context beyond that: free-window traffic distribution is not inferred, and Waply plans and taxes are excluded, which sets expectations about what the result does and does not cover.

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?

Three front-loaded sentences that carry the comparison scope, return shape, and exclusions with minimal waste. Nothing redundant, though the middle sentence about free-window inference is slightly dense for its information value.

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?

For a 7-parameter, no-output-schema tool, the description covers what comes back (totals, breakdowns, difference) and the key modeling caveats and exclusions. Only the relationship to the sibling calculation tool is left implicit, which is a minor gap.

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 86%, so the schema already documents most parameters in detail (service, utility, marketing, phoneCount, authentication, market). The description adds little per-parameter meaning, only the general notion of sharing the same volume across both cards, which is the baseline 3 case.

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: compare monthly message volumes across the current and October 2026 Meta rate cards, and names the returned artifacts (both USD totals, breakdowns, October-minus-current difference). This distinguishes it cleanly from the sibling calculate_message_cost, which produces a single cost rather than a two-card comparison.

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?

Frames the scenario (comparing the same volumes under two rate cards) and states it matches the web calculator, plus scoping exclusions (Waply plans, taxes). It does not explicitly name the alternative tool or state when not to use this in favor of calculate_message_cost, so it stops short of clear routing guidance.

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