ModelCostComparison

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

Annotations already mark the tool read-only, idempotent, and non-destructive. The description adds meaningful context beyond those: it uses current reviewed rates, excludes cache writes/storage/tools/taxes, and does not invoke a model. No contradiction with annotations.

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 short sentences with no filler. The main purpose is front-loaded in the first sentence, and the subsequent sentences add exclusions and behavioral facts without 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?

The description covers scope, exclusions, and the no-invocation behavior, and the output schema exists, so return values need no explanation. However, it does not clarify the optional expected_dataset_revision parameter or the role of max_input_tokens_per_request, leaving some gaps for a tool with nested inputs.

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, but it only loosely references cached input and text tokens. It does not explain model_id semantics, expected_dataset_revision, or max_input_tokens_per_request. The schema names are self-descriptive, but the description adds minimal parameter-level guidance.

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 ('Estimate'), a clear resource ('USD text-token subtotal'), and a precise scope ('one exact offer'). It also distinguishes this tool from siblings like compare_model_costs by emphasizing single-offer calculation rather than 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?

The description gives clear context: use this tool when you need a token-cost subtotal for one offer, not for comparing models or invoking a model. It does not explicitly name alternatives or state when-not-to-use, but the 'one exact offer' phrasing implies the boundary against sibling tools.

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

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.

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds valuable context that expired or unreviewed prices are informational only, indicating data freshness/validity caveats. This goes beyond the structured annotations.

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 one concise sentence that front-loads the action and includes the caveat. No wasted words.

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?

The description provides the core purpose and a caveat, and an output schema exists. However, the ambiguity between 'offer ID' and 'model_id' and the lack of sibling differentiation leave some gaps for a fully complete context.

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 has 0% description coverage, so the description must explain the model_id parameter. It refers to 'exact offer ID' but does not explicitly map model_id to that concept, leaving ambiguity about the parameter's meaning and format.

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 'Read' and resource 'USD text-token prices, tariff identity, provenance and freshness' for an exact offer ID, clearly distinguishing it from siblings that calculate or compare costs.

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?

No explicit guidance on when to use this tool versus calculate_cost, compare_model_costs, or list_models. The purpose implies reading prices, but no exclusions or conditions are stated.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable context beyond annotations: the default to 'current reviewed prices', the caveat that offers 'may still have unsupported billing modes', and the explicit limitation that it does not recommend model capabilities. These are substantive behavioral disclosures.

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 short sentences, each earning its place: the core purpose is front-loaded, followed by default behavior and an important caveat/scope limitation. There is no filler or redundant restatement of schema or annotations.

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?

With an output schema present and strong annotations, the description does not need to explain return values or safety. However, it omits operational details such as pagination semantics for cursor/limit and the meaning of query, which are relevant for correct invocation. The caveats about billing modes and capability recommendations add context, but the parameter handling gaps keep it from being fully complete.

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%, and the description provides no information about any of the six parameters. It does not explain how limit, query, cursor, status, provider_id, or pricing_tier should be used. The schema property names and the enum/default values provide some self-evident meaning, but the description fails to compensate for the complete lack of schema descriptions.

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 starts with a specific verb+resource: 'Find exact pricing offers and their IDs.' It clearly states the tool's output focus (pricing offers and IDs), and the closing 'No model capability recommendation' distinguishes it from capability-oriented tools. However, it does not explicitly name or contrast the sibling tools, so differentiation remains implicit.

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 no guidance on when to use this tool versus siblings like calculate_cost, compare_model_costs, or get_model_pricing. It notes the default status and billing-mode caveat, but these are behavioral facts rather than routing instructions. There are no explicit when-to-use or when-not-to-use statements.

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