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

Annotations already declare readOnlyHint and idempotentHint. The description adds valuable behavioral detail: avgCallMinutes defaults to 3 and is echoed in assumptions for reproducibility, and quote-only/unpriceable vendors return null (never a fabricated figure). This goes beyond the annotations to set expectations about output, without contradicting them.

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 reasonably concise given the complexity. It front-loads the core purpose, then explains edge cases (non-telephony, null) and defaults. No filler; each sentence earns its place. Could be slightly tighter but is well-structured.

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?

Without an output schema, the description explains what is returned: each plan's base monthly price, cheapest priceable plan per vendor, and null for unpriceable. It also covers the default for avgCallMinutes and how to list valid section slugs. Slight ambiguity remains about the exact response structure (array vs object), but overall it gives enough for an agent to call and interpret the result.

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 33% (only 'section' has a description). The description compensates by explaining that callsPerMonth is the chosen call volume, that avgCallMinutes defaults to 3 and is used for normalization, and how the two interact for telephony vs non-telephony themes. It adds meaning beyond the bare schema types and minimums.

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 ('Effective monthly cost per vendor'), with clear scope ('any theme at a chosen call volume') and the normalization logic (flat, per-minute, per-call). Distinguishes the two modes (telephony vs non-telephony) and explains the fallback for non-telephony themes, so the agent knows exactly what it computes. Far from tautology, it adds precision beyond the name.

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?

Provides explicit guidance on how to use the 'section' parameter (call list_sections or list_coverage, do not assume old set) and describes when the tool returns base monthly price vs null. It does not explicitly name sibling tools as alternatives, but the behavioral description helps the agent understand when it is relevant. Clear context, though no direct comparison to alternatives like get_cost_decoder.

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