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

Annotations already declare read-only, idempotent, non-destructive, and open-world behavior, so safety is covered. The description adds useful behavioral context beyond that: results are sorted cheapest first and cover every provider on OpenRouter, which helps set expectations for output ordering and completeness.

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?

A single sentence front-loads the core idea ('Same model, different providers') and then enumerates returned fields with the sorting rule at the end. No sentence is wasted and the structure is easy to parse.

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 low complexity, full schema coverage, rich annotations, and the presence of an output schema, the description supplies everything an agent needs: the comparison scope, returned dimensions, and ordering. Nothing critical is missing 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 100%, so the schema fully documents both parameters (model id/name and response_format enum). The description adds no additional parameter syntax or format details beyond what is already structured, so baseline 3 is appropriate.

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 action (compare providers for the same model) and lists the exact dimensions returned (price, context, max output, quantization, uptime), making it easy to distinguish from siblings like find_models or estimate_cost. An agent can tell at a glance that this tool is for provider-level comparison rather than model discovery or cost estimation.

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 phrase 'Same model, different providers' implies the scenario, but there is no explicit guidance on when to prefer this over siblings such as model_price_history or price_changes. Usage is inferable from the purpose but not stated, so it lands at the minimum-viable level.

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 cover read-only, idempotent, non-destructive, open-world. The description adds the useful result-ordering trait (cheapest first) and signals current pricing, but says nothing about currency, whether figures are estimates vs billed rates, or how model-name resolution failures behave.

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?

One line, front-loaded with the core action and scope, with the ordering detail appended. Nothing is wasted.

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 an output schema exists and schema coverage is total, the description need not explain return values. It conveys the essential framing (today's prices, cheapest first) for a 5-param tool; only edge-case behavior is unaddressed.

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%, so every parameter including 'calls', token counts, and response_format is already documented. The description adds no syntax or semantics beyond what the schema provides, 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 action (estimate cost) and resource (a workload across several models), plus the ordering (cheapest first). It is distinguishable from find_models and price_changes, though it never names them.

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 phrase 'at today's prices' implicitly contrasts with sibling tools like model_price_history and price_changes, so usage context is inferable. But there is no explicit when-to-use statement, no exclusions, and no routing to alternatives.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's job is to add operation-specific insight — and it does, by disclosing that 'cheapest' uses a blended price weighting of 3 input : 1 output tokens. That formula is not recoverable from annotations or the schema's bare 'Ranking.' default.

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 front-loaded sentences with zero filler: the first states scope and filters, the second qualifies the default sort's semantics. Every clause 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?

With an output schema present, return-format detail is rightly omitted, and the description covers the search filters, the default sort, and the ranking definition. It is complete enough to invoke correctly, only lacking routing guidance relative to sibling tools.

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 already 88%, giving a baseline of 3, and the description adds meaning on top by explaining how the sort='cheapest' option is computed. It does not, however, expand on any of the other seven parameters beyond what the schema already documents.

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 ('Search') and resource ('OpenRouter's live catalog') plus the four filter dimensions (name, capabilities, price ceilings, context size), so the agent knows exactly what it returns. It doesn't name any sibling (compare_providers, estimate_cost, price_changes) to draw a boundary, which keeps it short of a 5.

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?

There is no explicit when-to-use or when-not guidance and no mention of alternatives among the siblings (estimate_cost, price_history, compare_providers). Usage is only inferable from the stated filters, so the agent must guess whether to reach for this versus a cost-comparison tool.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered. The description adds genuine context about data provenance (archived copies since 2023) and what the output includes (per-change % and overall change), but says nothing about rate limits, coverage gaps, or freshness beyond 'today's price'.

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 tight sentences, front-loaded with the resource and time scope, then the returned content. No filler or repetition 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?

An output schema exists, so return-value explanation is not required, and the description covers data range and change reporting. The one gap is the absence of routing guidance among the four sibling pricing tools, which an agent would need in order to choose 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?

Schema description coverage is 100%, so both parameters (model, response_format) are already documented in the schema, including an example model id and enum values. The description only reinforces 'one model' per call and adds no format or syntax detail beyond the schema, so the baseline 3 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?

States a specific verb (retrieves price history) and resource (one model's pricing) with scope qualifiers: monthly granularity, since the model appeared on OpenRouter, plus today's price. An agent can distinguish this from siblings like price_changes or estimate_cost, which do not cover a single model's full historical timeline.

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 when-to-use or when-not-to-use guidance is given, and no sibling tool is named as an alternative. The existence of a sibling named price_changes makes the omission notable, since the agent must guess which tool covers change history versus general price history.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds what the report actually contains (drops, increases, free models, model counts), which is useful content-level context, but it says nothing about aggregation window behavior, freshness, or data source. Adequate but not rich.

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?

A single front-loaded sentence that enumerates the report's contents with no filler. It is slightly list-like and could be tightened, but nothing in it is wasted.

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-format explanation is rightly omitted, and the three parameters are simple. However, the description leaves the `limit` parameter unexplained and introduces a 'since a month' claim inconsistent with the documented 3-month default, gaps an agent would notice when setting the window.

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 67%: `since` and `response_format` are documented in the schema, while `limit` is not. The description's 'since a month' loosely gestures at the comparison window but actually conflicts with the schema's own default of '3 months ago', so it adds ambiguity rather than meaning for the one parameter it touches. Baseline 3 is appropriate.

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 resource (LLM pricing) and an explicit scope (changes over a period), enumerating the outputs: biggest drops/increases, newly free models, models added/removed. It does not, however, distinguish itself from close siblings like model_price_history or compare_providers, leaving the agent to infer the difference.

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?

There is no when-to-use guidance, no stated alternatives, and no exclusions. Given siblings such as model_price_history (per-model history) and compare_providers (cross-provider comparison), the agent needs a routing rule that this description never supplies.

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