Compute Screener

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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so the safety profile needs no restating. The description adds genuinely non-obvious behavior: data is pulled live from each exchange's public market-data API within the last minute, and specifying a GPU returns additional benchmark, provider-average, and per-exchange last-price/24h-volume data. The freshness guarantee and conditional expansion are valuable context beyond the 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?

Front-loaded with the core output (price index and changes) before the conditional extras, and every clause carries information. The second sentence is dense and slightly run-on, but nothing is redundant or 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?

With no output schema, the description carries the burden of describing returns, and it does so reasonably: index values, 1D/1W/1M deltas, page links, and the fuller payload when a GPU is specified. The exact shape of the all-GPU response is only loosely sketched, which keeps this short of a 5.

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% and the enum is fully documented, so the baseline is 3. The description earns extra credit by explaining what the parameter changes in the response — passing a GPU value switches on benchmark contracts, standardized provider averages, and exchange-level data — which is semantics the schema alone does not convey.

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: latest GPU rental price index in USD per GPU-hour with 1D/1W/1M changes and per-GPU links. This is clearly distinct from get_token_prices, but the description never names or differentiates itself from get_price_history, which is the closest-sounding sibling.

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 conditional 'Give one GPU to also get...' plus the schema note 'omit for all listed GPUs' implies how the optional parameter selects scope, so usage is inferable. However there is no explicit statement of when to call this versus get_price_history (e.g., current index vs. historical series), leaving the agent to guess.

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, closed-world), so this is additive: the description discloses ordering (oldest first), sampling cadence (daily vs weekly before a cutoff) and the coverage start dates per entity. That is real behavioral context an agent cannot get from the schema.

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 what the tool returns, then the coverage/cadence caveats. No filler, every clause carries information.

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 no output schema, the description must describe results, and it does: units, ordering, granularity and start dates. It stops short of stating the default 30-day window behavior at the top level or what the series looks like per point, which is a minor residual gap.

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 does add meaning: the single `name` parameter spans two disjoint families whose units differ (USD/GPU-hour vs USD/1M tokens), which tells the agent how to interpret results per enum value. It adds little on `days` beyond what the schema states.

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 the resource (price history), the two entity types it covers (one GPU or one AI company), and the units for each (USD per GPU-hour vs USD per 1M tokens). That implicitly separates it from the snapshot siblings get_gpu_prices/get_token_prices, but it never names them, so the 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?

Usage is only implied: an agent must infer that this is the time-series tool while get_gpu_prices and get_token_prices return current values. There is no explicit when-to-use, when-not-to-use, or named alternative.

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 safety (readOnly, idempotent, closed-world), so the description's job is narrower; it adds genuine context by defining the blended index formula, the currency/unit basis, and the three change horizons returned. It does not discuss ordering, staleness, or coverage of the company list, but for a read-only snapshot tool this is solid added value.

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, zero filler, and the core metric definition is front-loaded before the optional-parameter behavior. Nothing could be cut without losing information.

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 optional-parameter read-only tool with no output schema, the description supplies the metric definition, units, time windows, and what changes when a company is specified — everything an agent needs to call it 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 coverage is 100% and the enum already documents the accepted companies, so the baseline is 3; the description earns an extra point by explaining the semantic consequence of passing a company (response expands to per-model usage shares and posted prices) rather than just repeating the field.

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+resource ('Latest token price index per AI company') and pins down the metric's definition (USD per 1M tokens, 3:1 input/output blend) plus the change windows returned. It does not explicitly name the sibling tools (get_gpu_prices, get_price_history), but 'Latest' implicitly separates it from a history endpoint.

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?

'Give one company to also get its models' usage shares and posted prices' clearly explains the conditional benefit of supplying the optional parameter versus omitting it for the full list. No explicit exclusions against get_price_history are given, 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.