Sideways

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

Annotations already declare readOnlyHint=true, and the description is consistent with that. It adds useful behavioral context beyond the annotations: the result is random, and the call returns a 'labeled strategy card.' It does not overpromise side effects or downstream consequences.

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 short and front-loaded, but it repeats the 'Use when' trigger in slightly different forms ('Use when stuck...', 'Best for...', 'Use this when...'). This redundancy could be collapsed without losing meaning. Still, every sentence contributes to purpose, usage, or output.

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 zero-parameter, read-only random card generator, the description covers the essential context: what it returns, why you would use it, and what mindset it serves. There is no output schema, so the description's explicit statement about the returned 'labeled strategy card' fills that gap adequately.

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, so there is no parameter semantics to document. The schema coverage is trivially 100%, and the baseline for a no-parameter tool is 4; the description adds no contradictory or confusing parameter information.

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-plus-resource: 'Get a random Disrupt strategy.' The category 'Disrupt' distinguishes it from the sibling tools (embody, expand, pause, reduce, reframe) without needing to inspect them. It also foreshadows the return value ('labeled strategy card').

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 clear, concrete use conditions: 'stuck in safe patterns, avoiding risk, or when work feels too polished or predictable,' plus a list of when to apply it ('break patterns, embrace chaos, make destructive moves, honor mistakes'). It does not explicitly name alternatives or exclusion criteria, 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.

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

Annotations already declare readOnlyHint=true, so the agent knows this is a safe read operation. The description adds that the tool returns a 'labeled strategy card' and that it helps 'shift your perspective and break through blocks,' which is useful context. However, it doesn't disclose details like whether the result is truly random each call or whether there are any side effects, though the readOnly annotation covers the main safety concern.

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 concise and front-loaded with the core action ('Get a random Embody strategy') followed by usage guidance. It is slightly repetitive ('Use this when' appears twice), but the overall structure is clear and every sentence adds value.

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 zero-parameter, read-only tool with no output schema, the description is largely complete. It explains what the tool does, when to use it, and what the return value is ('labeled strategy card'). The only minor gap is not specifying the exact format or content of the strategy card, but this is not critical for a random strategy generator.

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, so the schema provides no parameter semantics to clarify. The description compensates by explaining what the tool does and what it returns, which is sufficient for a no-parameter tool. Baseline 4 is appropriate because there are no parameters to document.

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 a random Embody strategy card, with a specific verb ('Get') and resource ('Embody strategy'). It distinguishes itself from siblings by naming the category (Embody) and describing the body-based approach, though it doesn't explicitly name sibling 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?

The description gives explicit when-to-use guidance: 'when too much in your head, experiencing physical tension, or disconnected from intuition' and 'Best for grounding abstract work in physical reality.' It also lists the use case category ('physical, sensory, body-based approaches to creative problems'), which helps an agent select this over sibling categories.

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 openWorldHint=false, so the description does not need to cover side effects. It adds behavioral value by revealing that the result is 'random' (non-deterministic) and that it returns a 'labeled strategy card', which is not implied by the annotations. There is 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 somewhat repetitive: 'Use when solutions feel too minimal, when avoiding decisions, or when there's room to explore more possibilities' overlaps with 'Best for breaking self-imposed limitations' and the later list 'add more, elaborate, embrace abundance, do both'. It could be tightened to a single concise set of triggers without losing meaning. Still, it is front-loaded with the core action and not overly verbose, so it remains acceptable.

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 parameters and no output schema, the description covers the essential aspects: what it does, when to use it, and what it returns. The random nature is disclosed. Given the sibling tools, the category name 'Expand' provides enough context to differentiate. Nothing critical is missing for an agent to call this tool 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 tool has zero parameters, so the schema trivially covers 100% of them. The description does not need to add parameter information, and the baseline for 0 parameters is 4. The description does not introduce any parameter-related confusion.

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 verb 'Get' and the resource 'random Expand strategy', specifying the category 'Expand' which distinguishes it from siblings. It also describes the output as a 'labeled strategy card', giving a concrete sense of what the tool delivers. This is not a tautology; it adds specific meaning beyond the name.

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 explicit usage triggers: 'when solutions feel too minimal', 'when avoiding decisions', 'when there's room to explore more possibilities', and a list of keywords like 'add more, elaborate, embrace abundance, do both'. It clearly states when to use this tool, though it does not explicitly mention when not to use it or name alternatives. Since sibling tools exist, a direct contrast would elevate this to a 5, but the guidance is strong.

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 indicate readOnlyHint=true, and the description adds behavioral detail about randomness and the return format ('labeled strategy card'). It clarifies what the agent can expect without overclaiming side effects.

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 reasonably short and front-loaded with the core action. There is slight redundancy between 'gaining clarity through distance and reflection' and 'shift your perspective and break through blocks,' but it remains efficient overall.

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, parameterless read-only tool, the description covers what it does, when to use it, and what it returns. No important context 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 tool has zero parameters, so there is no parameter semantics to clarify. The baseline of 4 applies because the description handles all the semantic burden that would otherwise be needed.

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 action ('Get a random Pause strategy') and names the resource, making the tool's purpose unmistakable. The category name 'Pause' also distinguishes it from sibling strategy-category 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?

Provides clear, concrete when-to-use signals: rushing, feeling frantic, unable to see the forest for the trees, rest/reflect/step back. It does not explicitly mention when not to use it or direct to an alternative, but the context is strong enough for an agent to select it appropriately.

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, so the agent knows this is a safe read operation. The description adds that the tool 'Returns a labeled strategy card to help shift your perspective and break through blocks,' which gives some context about the output format and purpose. However, it doesn't disclose details like whether the result is truly random, whether repeated calls can return the same strategy, or any rate limits. With annotations covering the safety profile, a 3 is appropriate – the description adds some value but not rich behavioral context.

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 concise and front-loaded with the core function. The first sentence states what it does, the second gives usage context, and the third lists trigger keywords. The final sentence about the return value is slightly redundant with the first sentence but adds useful context. No wasted words, though the structure could be slightly tighter.

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 parameterless, read-only tool with no output schema, the description is quite complete. It explains what the tool does, when to use it, and what it returns. The only minor gap is that it doesn't specify whether the 'random' selection is truly random or if there's any weighting, and it doesn't describe the exact structure of the 'labeled strategy card.' However, given the tool's simplicity, these are minor omissions.

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 0 parameters, so the schema is trivially complete. The description doesn't need to explain parameters. The baseline for 0 params is 4, and the description adds value by explaining what the returned strategy card is for, which is more than enough for a parameterless tool.

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's function: 'Get a random Reduce strategy.' It names the specific resource (Reduce strategy) and the verb (get), and the sibling list shows other category-specific tools, so the purpose is unambiguous. The description also lists trigger keywords like 'simplify, subtract, remove, clarify, focus on essentials,' which further 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?

The description explicitly states when to use this tool: 'Use when overwhelmed by complexity, dealing with too many options, or when clarity is needed.' It also provides a clear list of use-case keywords. While it doesn't explicitly name alternatives, the sibling tools are category-specific, and the description's trigger words make the selection criteria clear. The 'Best for cutting through noise and finding the core' adds practical 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?

The description adds value beyond the annotations: it clarifies that the tool is non-destructive (readOnlyHint=true) but also explains the output is a 'labeled strategy card' that helps shift perspective. It doesn't contradict annotations. It adds contextual detail (random selection, card format) but doesn't delve into specifics like whether the card has title, description, or instructions—though with no output schema, that gap is acceptable. Without annotations, it would still be decent, but with annotations covering read-only, the description earns a 4 for adding behavioral context.

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 relatively concise, but it repeats the purpose multiple times: 'stuck in a single way of thinking, facing opposition, or need to see the problem from a completely different angle' and later 'change your perspective, reverse assumptions, adopt alternative viewpoints' are redundant. Some trimming would improve, but it's still front-loaded with the core action (random Reframe strategy) and essential guidance. It's not wasteful enough to drop below 4.

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 zero-parameter tool with no output schema, the description covers what an agent needs: when to call it and what to expect (a labeled strategy card). It doesn't specify the exact structure of the card, but that's a minor gap. It lacks explicit exclusions (when not to use), but the purpose is narrow, so completeness is high. The mention of the card's purpose adds context, so a 4 is warranted.

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?

With zero parameters and 100% schema coverage (which is trivial for empty properties), the description doesn't need to explain parameters. The baseline for zero params is 4, and the description instead focuses on usage context, which is appropriate. It adds no parameter-specific info because there are none, but that's fine.

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 it returns a random Reframe strategy, with a specific purpose (breaking mental ruts) and explicitly mentions usage scenarios (stuck, opposition, different angle). It also differentiates itself from siblings by naming the specific category (Reframe), though it doesn't explicitly compare to siblings, the category name is distinctive enough.

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?

Provides explicit 'when to use' conditions: 'when stuck in a single way of thinking, facing opposition, or need to see the problem from a completely different angle' and 'Best for breaking out of mental ruts.' It also lists example use cases: 'change your perspective, reverse assumptions, adopt alternative viewpoints.' This is clear guidance for an agent, though it doesn't mention when NOT to use it, but given the narrow purpose, it's sufficient.

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