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

Annotations already establish this is read-only, idempotent, and non-destructive, so the bar for added value is met well. The description discloses the statistical model (Poisson process), live inputs, the specific computed outputs, and the caveat that variance dominates at small hashrates, making the average misleading.

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 front-loaded with the core purpose and output, then gives concrete use cases and sibling routing. Every sentence earns its place, including the variance caveat and alternative tool references, without unnecessary repetition of schema details.

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 adequately enumerates return values: mean time, probabilities over standard horizons, and percentile waiting times. It also covers when to use the tool, when not to, and what distinguishes it from related tools, making it complete for agent selection and 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 baseline is 3; the schema already thoroughly documents coin_id, hashrate, hashrate_unit, power_watts, and electricity_cost_usd_kwh. The description adds useful conceptual framing by connecting parameters to the Poisson model and electricity cost, but it does not add substantial syntax or format details beyond 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?

The description identifies a specific verb and resource: computing solo mining odds via a Poisson process over network difficulty and hashrate. It clearly distinguishes itself from siblings by naming get_cost_of_production and get_coin_oracle as alternatives for different questions.

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 example questions that should route to this tool, such as 'how long would it take to solo mine a Bitcoin block with 100 TH/s'. It also states exclusions: pooled mining economics or general profitability should use get_cost_of_production, and raw network state should use get_coin_oracle.

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, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond that: data provenance from stratum collector nodes, the confidence block fields (pool agreement count, live/static fallback, observation age), and the explicit error-rather-than-zeros policy for stalled collectors.

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?

Four dense sentences front-load the return fields, then explain reliability semantics, give usage examples, and route to alternatives. Every sentence earns its place and there is no redundant wording.

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 one well-documented required parameter and no output schema, the description supplies sufficient information about the return payload, confidence metadata, error behavior, and sibling alternatives. Nothing an agent needs to invoke this tool correctly is missing.

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 input schema already provides 100% coverage for the single coin_id parameter, including format, examples, and ambiguous-input handling. The description does not add parameter-specific details, but with full schema coverage the baseline of 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 the exact resource ('network state for one Proof of Work chain') and enumerates the fields returned, making the tool's purpose unmistakable. It explicitly contrasts with sibling tools get_cost_of_production and calculate_solo_mining_odds, so an agent can tell them apart without opening their 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 concrete query examples ('what is Kaspa's current difficulty', 'network hashrate of Monero', 'current block reward') and explicit routing guidance: use get_cost_of_production for economics and calculate_solo_mining_odds for mining probability. This is clear, actionable when-to-use information with named 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 declare readOnlyHint, idempotentHint, and destructiveHint, so the description doesn't need to restate safety. It adds useful behavioral detail: the return fields, the meaning of a reference-machine change indicating the efficiency frontier moved, and the effect of a custom electricity rate. It does not contradict 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 dense but every sentence earns its place: a crisp definition, the output fields, an optional-input note, concrete use cases, and sibling routing. The definition is front-loaded and there is 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?

Although there is no output schema, the description enumerates the return values (CoP in USD, spot, gross margin, above/below water, reference machine and tariff, 30-day trend). It also covers usage context, parameter semantics via schema, and alternative tools, so an agent has everything needed to select and 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?

Schema description coverage is 100%, so the schema fully documents coin_id and electricity_cost_usd_kwh. The description adds interpretive context by explaining that CoP is computed on the most efficient hardware and that a custom electricity rate is accepted, but it intentionally leaves parameter-level details to 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?

The description states a specific verb and resource: it computes the all-in electricity cost of mining one unit of a Proof of Work coin on the most efficient tracked hardware, compared to spot price. It clearly distinguishes itself from siblings by naming the object of interest (a coin's production cost) and explicitly pointing to get_hardware_benchmarks and calculate_solo_mining_odds as different 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 gives explicit use cases ('is mining X profitable', 'what does it cost to produce one Monero', 'are miners underwater', 'break-even electricity price'). It also gives explicit exclusions and alternatives: use get_hardware_benchmarks for a specific rig and calculate_solo_mining_odds for block-finding probability.

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, openWorldHint=true, idempotentHint=true, destructiveHint=false, covering the safety profile. The description adds behavioral context beyond that: results are ranked by profitability, results are capped (with a hint to request a higher limit), and market price may be an observed listing or a model estimate. These are useful traits not present in annotations. It doesn't add rate limits or error behavior, but with annotations covering safety, the extra detail is sufficient. 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?

The description is slightly long but every sentence adds value: first sentence states purpose and key features, second gives example queries, third explains ranking and capping, fourth routes to an alternative. It's front-loaded with the core purpose and well-structured. It's not overly verbose, though it could be trimmed slightly; still, the density is justified by the tool's complexity.

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?

Despite no output schema, the description lists the return fields (hashrate, power draw, gross revenue, net profit, market price, price type), explains ranking and capping, provides example queries, and gives an alternative tool for other use cases. With 5 parameters, this description covers all essential aspects an agent needs to call it correctly: what it does, when to use it, key behaviors, and alternatives. Nothing critical is missing.

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 input schema has 100% description coverage for all 5 parameters, so the schema already documents each parameter thoroughly (type enum, limit range and default, query min length, coin_id pattern, electricity cost default and impact). The tool description adds only marginal semantic value, e.g., mentioning that electricity rate affects profitability and hinting at the limit cap. Baseline for high coverage is 3, and the description doesn't significantly exceed that.

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 and resource (get hardware benchmarks), and clearly defines what it does: matches mining hardware to coins, ranks by net USD/day, and covers ASICs/GPUs/CPUs. It explicitly distinguishes itself from get_cost_of_production, which is a sibling, by stating the alternative use case. The purpose is unambiguous and unique among 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?

The description gives multiple concrete example queries ('what should I mine with an RTX 4090', 'best ASIC for Scrypt', etc.), explains the ranking basis (profitability, not alphabetical), warns about result capping and advises asking for a higher limit, and explicitly directs to get_cost_of_production when the user wants coin economics independent of hardware. This is explicit when-to-use and when-not-to-use guidance with an alternative named.

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 readOnly, openWorld, idempotent, and non-destructive behavior. The description adds useful behavioral context beyond that: results are aggregated from third-party feeds, returned as quoted external content with publisher and relevance score, and not represented as BackPow statements of fact.

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 compact and well structured: it states what the tool returns, clarifies the nature of the content, gives concrete usage guidance, and names alternatives. Every sentence earns its place with no 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?

With no output schema, the description still tells the agent what to expect: quoted external content, publisher, and relevance score. Along with schema-defined parameters and safety annotations, this is sufficient for correct invocation. Minor gap: no explicit mention of ordering or time window, but 'recent' plus relevance scoring reasonably implies the behavior.

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 input schema has 100% description coverage for all three parameters, so the schema carries the explanatory burden. The description adds only a brief mention of the optional coin filter, which aligns with coin_id but does not substantially extend parameter understanding.

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 identifies the tool's resource ('news items about Proof of Work mining and network events') and the optional coin filter. It also differentiates the tool from its siblings by noting it returns quoted external content with relevance scores, not first-party factual statements.

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 explicit when-to-use guidance with concrete examples ('a halving, a difficulty swing, a pool outage, a chain upgrade') and points to alternative tools for numeric questions ('For numbers rather than narrative, use get_coin_oracle or get_cost_of_production').

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, idempotent, and non-destructive, and the description adds important behavior beyond that: pagination expectations, the fact that profitable_only is resolved only for the returned page, and that the response includes the algorithm list for discoverability. This directly helps the agent interpret small or partial results.

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 compact and well-structured: definition, optional filters, output hint, use cases, and a necessary pagination warning. Each sentence earns its place, and the core purpose is front-loaded.

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?

Despite having no output schema, the description explains what the response will contain, how filtering and pagination work, and what edge cases to expect (e.g., small result sets from profitable_only). The tool is fully callable with the provided guidance.

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 all five parameters are already documented with meaningful descriptions. The description reinforces the roles of algorithm and profitable_only but does not add substantive new parameter meaning beyond what the schema provides.

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 first sentence immediately identifies a specific verb ('Paginated index') and resource ('Proof of Work networks BackPow tracks') plus the returned fields. It also differentiates from siblings by framing this as the catalogue/browsing tool, not a calculation, cost, benchmark, or news tool.

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 explicit use cases: find networks for an algorithm, browse the catalogue, or resolve an ambiguous coin reference. It does not explicitly name when not to use it or list sibling alternatives, but the context is clear enough that an agent can choose it appropriately.

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