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

Annotations already mark this as read-only and idempotent. The description adds meaningful behavioral context: it returns 'supported results plus per-offer exclusions' and warns that 'equal token counts are an assumption, not tokenizer equivalence.' This goes beyond the annotations 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?

Three sentences with no filler: the main purpose is front-loaded, the return behavior is stated, and the critical caveat is placed at the end. Every sentence earns its place.

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 description. The description covers the core comparison semantics, the exclusion behavior, and a key assumption. It could mention how to specify the pricing snapshot, but the overall picture is 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%, so the description must compensate. It clarifies that model_ids must be 2–20 exact offers and that token counts must be identical, which maps to usage. However, it does not explain cached_input_tokens, max_input_tokens_per_request, or expected_dataset_revision beyond the vague 'one pricing snapshot' phrase, leaving gaps.

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 states a specific verb ('Compare'), a precise resource ('2–20 exact offers for identical text-token counts'), and a key constraint ('using one pricing snapshot'). It clearly distinguishes this from siblings like calculate_cost or list_models by focusing on multi-offer comparison rather than single calculations or model listing.

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 gives clear context for when to use the tool: when comparing 2–20 offers under identical token counts and a single pricing snapshot. It does not explicitly name alternatives or state when not to use it, but the conditions are specific enough to guide selection.

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