AI Wave

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

With no annotations, the description carries the burden. It discloses a key behavioral trait: missing benchmark scores are marked as untested rather than represented as low values, preventing misinterpretation. It also says it aligns fields. It does not mention read-only semantics or error handling, but the comparison verb and output description make the non-mutating nature clear.

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?

Two sentences: the first fronts the purpose, the second gives usage guidance and a crucial semantic clarification. No filler words; every clause contributes.

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?

There is no output schema, so the description must convey what the tool returns. It lists price, context, benchmark scores per subject, and monthly cost, and clarifies missing-score handling. It could be more specific about the return format (e.g., table vs object), but for the stated purpose it is adequately 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 coverage is 100%, so baseline is 3. The description adds meaning by mapping 'two or more models' to the ids parameter and 'at a given volume' to monthlyMillionTokens, explaining the purpose of the cost-estimation parameter without repeating schema details.

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 ('put side by side'), resource ('models'), and enumerates the comparison dimensions (price, context, benchmark scores, monthly cost). It explicitly contrasts with get_model by saying 'Use this instead of calling get_model repeatedly', which distinguishes it from siblings.

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?

It gives explicit usage guidance: when comparing multiple models, use this instead of calling get_model repeatedly. It also explains the benefit—aligned fields and marking untested subjects—so the agent knows when the tool is the right choice versus the single-model getter.

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?

No annotations are provided, so the description carries the burden. It helpfully discloses the default 75/25 input/output mix and the monthly framing, but says nothing about required currency/permission context, error behavior for unknown ids, or what exactly is returned beyond 'USD and KRW'.

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 lead with the output and scope before the rationale. The middle sentence ('hard to reason about directly') is mildly chatty but earns its place by justifying the tool's existence.

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 simple calculation tool with 100% schema coverage and no output schema, the description supplies the key assumptions (default token volume, 75/25 mix, dual currency) an agent needs to call it correctly. Only edge-case or error behavior is unaddressed, which is minor here.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning: it explains why inputShare exists ('Input and output are mixed 75/25 unless you pass your own split') and frames the monthly interpretation of monthlyMillionTokens, going beyond the raw schema text.

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 names a specific verb (estimate) and resource (monthly cost) and states the scope precisely: per model, at a given token volume, in USD and KRW. It clearly is the cost-estimation tool among price/model lookup siblings, though it never explicitly contrasts itself with get_price_history.

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?

Usage is implied – pass a model id to turn per-million token prices into a monthly bill – but there is no explicit when-to-use/when-not guidance or routing to alternatives like get_price_history or compare_models. The 'unless you pass your own split' clause hints at an optional override but doesn't frame tool 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?

With no annotations provided, the description carries the full burden and does so well: it discloses the ranking criterion (performance closeness), the exclusion rule (context window less than half the original), the returned fields (score, price, context deltas), and that the tool does not make the decision for the user.

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 three dense sentences with no filler. It front-loads the purpose, then explains ranking logic, exclusion criteria, and output contents in a logical order.

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 single-parameter tool with no output schema and no annotations, the description covers why to use it, how results are ranked, what is excluded, and what is returned. An agent has enough information to invoke it correctly.

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 already documents the id parameter at 100%, and the description adds context that this id represents the original/gone model to be replaced. This clarifies the role of the parameter beyond the schema's type-level description.

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 purpose: find a replacement or fallback when a model is gone. It also distinguishes itself from sibling tools like search_models or compare_models by focusing on substitution rather than general discovery or 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?

It clearly identifies when to use the tool ('when a model is gone or you need a fallback'), giving the agent a concrete trigger. It does not explicitly name sibling alternatives or state when not to use it, but the usage context is unambiguous.

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?

No annotations are provided, so the description carries the full burden. Describing returned fields implies a read-only lookup, but it says nothing about permissions, errors for unknown ids, caching, or rate limits. It adds some value (the returned data categories) but leaves the behavioral profile largely inferred.

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?

Two sentences, front-loaded with the return contract and followed by the one parameter's format. No filler.

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 one-parameter lookup with no output schema, the description covers what is returned and what the id may be. Only error/not-found behavior is unaddressed, which is a minor gap at this complexity.

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, and it does: it explains that `id` accepts either an OpenRouter id (with a concrete example, anthropic/claude-opus-5) or a Hugging Face repo id. This is the key invocation detail and is not present in the schema.

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 resource and the exact data returned (pricing, context length, catalog status), scoped to a single model. This clearly distinguishes it from siblings like compare_models and estimate_cost, though it never names an alternative explicitly.

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 single-model scope implies when to use it over compare_models, but there is no explicit when/when-not guidance or mention of alternatives. A caller must infer the routing from scope alone.

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?

With no annotations, the description carries full behavioral burden and exceeds expectations. It discloses important semantic details: each entry holds until the next one, and history starts when AI Wave began recording rather than at model launch. These caveats manage user expectations and are not evident from the schema or tool name.

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, all informative with no filler. The primary purpose is front-loaded, and the behavioral nuances about entry semantics and data coverage are placed after the core statement, making it easy to parse and act on.

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?

Given the simple single-parameter tool and no output schema, the description is mostly complete: it specifies the resource, the output concept, and two important caveats. It stops short of detailing the exact response structure, but such detail is arguably unnecessary for this straightforward lookup tool.

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 100% and the sole parameter is documented with a clear description ('OpenRouter id or Hugging Face repo id'). The tool description adds no extra param detail, so the baseline of 3 applies because the schema handles parameter semantics.

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 clearly states the tool returns price history for one model, including when the price changed and to what. It differentiates itself by emphasizing the single-model scope and the specific question it answers ('was this cheaper last month?'), which separates it from sibling tools like compare_models and list_model_changes.

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 clear context: the public catalog exposes only current price, so this tool is for historical price lookups. It implies the appropriate use case without explicitly naming alternatives or stating when not to use it, so the guidance is clear but not fully explicit about exclusions.

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?

No annotations are provided, so the description carries full behavioral burden. It usefully discloses that price changes are collapsed to one per model with the raw count kept, and states the relevant time windows. However, it leaves 'top 5' undefined and does not state the output shape or whether this is a read-only operation, so disclosure is partial.

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?

Two dense sentences carry the full value: the first enumerates the returned summary components, the second gives usage direction. There is no filler or redundant restating of the tool name.

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 the tool's contents, time windows, aggregation behavior, and preferred usage over the sibling. It is slightly incomplete because 'top 5 models' lacks a defined ranking criterion and there is no output schema to clarify the return shape, but the tool is low-complexity and no-parameter, so this is close to sufficient.

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 tool has zero parameters and an empty input schema, so there is no param documentation burden for the description. The baseline of 4 for no-parameter tools applies.

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 exactly what the tool returns: top 5 models, climbers, 24h price changes, and 7-day new listings. It also explicitly contrasts itself with list_model_changes, so an agent can distinguish it from the closest sibling without opening schemas.

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?

It gives an explicit when-to-use instruction: 'Use this instead of paging list_model_changes and re-deriving the summary.' This names the alternative and the condition that selects this tool, which is strong routing guidance.

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?

With no annotations, the description carries the burden and discloses useful behavior: normalization from multiple sources, deduplication per model, a status of official or pending review, and a since/latest polling contract. It omits auth, rate limits, and failure behavior, but covers the important traits for a read-only change feed.

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 front-load the purpose, then add provenance/deduplication behavior and polling instructions without significant fluff. The source list is slightly long, but each clause contributes.

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 tool with no output schema and no annotations, the description covers purpose, sources, and polling, but leaves the response item shape largely implicit beyond `latest` and a status marker. An agent can call it, but would benefit from knowing what fields each change entry contains.

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 already describes limit, model, and since; the description adds little per-parameter value beyond framing `since` as a polling cursor. It enumerates change categories which partially supports the undocumented `type` enum, but omits `open_source_surge`, so it does not fully compensate for the 25% schema coverage gap.

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 that the tool returns changes across AI models (new releases, price changes, API changes, deprecations) and cites its data sources, so the core purpose is clear. It does not explicitly contrast itself with siblings such as get_price_history or search_models, so differentiation is left to inference.

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?

It gives explicit polling guidance: call with `since` in unix seconds and feed the returned `latest` back next time. It does not state when to avoid this tool or name alternatives, so there is clear context but no exclusions.

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?

With no annotations, the description carries the behavioral burden. It discloses that results are ranked by measured performance, that benchmark scores and price are returned together, and that sorting by subject changes the ranking emphasis. It does not mention default ordering or pagination, but the core behavior is clearly surfaced.

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 each earn their place: the first states the function, the second gives the canonical query and output value, and the third explains subject-based sorting. There is no filler or repetition of the input schema.

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?

In the absence of annotations and an output schema, the description covers purpose, ranking behavior, result contents, and a sorting refinement. It does not describe return shape beyond score/price or justify when this tool beats its siblings, but for a stateless search endpoint the essential context is present.

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 coverage is 89%, so the schema already documents most parameters. The description maps high-level concepts (budget, context, capability, subject sorting) onto parameters but adds no new parameter-level detail; it also does not compensate for minContext lacking a schema description.

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?

Description opens with a specific verb-resource pair—'Shortlist models by budget, context and capability, ranked by measured performance'—and pins the exact question it answers ('which model should I use for X'). The mention of subject-specific sorting further differentiates it from generic model lookup tools.

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?

It names the canonical use case: answering model-selection questions where benchmark scores and price should be visible together. It does not explicitly compare against sibling tools like compare_models, estimate_cost, or find_replacement, nor state when not to use it, so it stops short of a 5.

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