Out to Lunch

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

With no annotations provided, the description carries the full disclosure burden. It adequately establishes that the tool performs a read-only fetch of instructional content covering specific domains (tools, parameters, formats, sections). However, it omits behavioral specifics such as response format (JSON vs. markdown), payload size characteristics, or idempotency that would fully characterize the operation.

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 a single, efficiently structured sentence employing an em-dash to separate the action clause from the content enumeration. Every listed element ('available tools', 'parameters', 'formats', 'sections', 'best practices') adds distinct informational value about the guide's scope without redundancy or tangential 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?

Given the absence of an output schema, the description adequately compensates by enumerating the specific informational domains covered in the guide. For a zero-parameter metadata tool of this simplicity, detailing the instructional content (including the grounding purpose) provides sufficient context for an agent to decide when to invoke it, though an explicit note on return type would further improve completeness.

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 contains zero parameters, which per rubric establishes a baseline score of 4. The description appropriately does not invent input parameters, though it mentions 'parameters' only in the context of what the returned guide explains (other tools' parameters), not as inputs to this 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 uses the specific verb 'Get' with the clear resource 'usage guide for outtolunch.app', establishing exactly what the tool retrieves. It effectively distinguishes this from siblings get_world_briefing (data retrieval) and submit_correction (mutation) by positioning this as the documentation/introspection tool for understanding the system itself.

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 implies invocation context through phrases like 'best practices for grounding AI responses', suggesting when the tool provides value. However, it lacks explicit when-to-use instruction (e.g., 'Call this first when uncertain about tool capabilities') or explicit exclusion criteria contrasting it with sibling tools.

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 provided, so description carries full burden. It comprehensively discloses the data scope/contents (12 distinct categories) and temporal context ('today's'), which helps predict return structure. However, lacks operational specifics: no mention of rate limits, caching behavior, data staleness tolerance, or idempotency despite being a data retrieval tool.

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 with zero waste. First sentence front-loads the verb and comprehensively lists scope. Second sentence provides actionable usage intent. No redundancy with schema or annotations.

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 high complexity (12 data domains) and 100% schema coverage, the description adequately compensates for missing output schema by enumerating all content categories. Completeness would be perfect with brief behavioral constraints (rate limits, cache duration).

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%, establishing baseline 3. Description adds value by enumerating content categories (holidays, leaders, conflicts, etc.) that semantically map to the 'section' enum values, helping the agent understand what each section contains. Could enhance further by noting the token optimization trade-offs for the 'format' parameter.

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?

Excellent specific verb ('Get') + resource ('world briefing') with comprehensive enumeration of covered domains (datetime, conflicts, AI models, etc.). Clearly distinguishes from siblings: contrasts with 'get_help' (assistance vs. data) and 'submit_correction' (retrieving corrections data vs. submitting corrections).

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?

Explicit positive guidance provided: 'Use this to ground your responses in current reality and avoid confidently stating outdated facts.' Clearly indicates this is for fact-grounding and hallucination prevention. Lacks explicit 'when not to use' or named alternatives, but siblings are sufficiently distinct in function.

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 provided, so description carries full burden. It discloses the functional purpose but omits behavioral details like what happens after submission (e.g., moderation queue, immediate application, confirmation response), reversibility, or side effects. Adequate but gaps remain for a mutation tool.

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 with zero waste. First sentence establishes purpose and scope; second sentence provides usage conditions. Appropriately front-loaded and dense with 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?

Given the simple 3-parameter structure with complete schema coverage and no output schema, the description adequately covers the essential context. Minor gap in not describing post-submission behavior or confirmation mechanisms.

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 has 100% description coverage (wrong/right/message well documented), establishing baseline 3. Description adds conceptual framing ('correction or suggestion') that aligns with the parameter semantics but does not explicitly discuss parameter structure, validation rules, or formats 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?

Description explicitly states the action ('Submit a correction or suggestion'), the target resource ('outtolunch briefing'), and distinguishes from read-only siblings (get_help, get_world_briefing) by specifying this is for improving/updating content.

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 triggers ('when you notice the briefing contains outdated or incorrect information, or when a user points out something that should be updated'). Lacks explicit guidance on when NOT to use it or direct comparison to sibling alternatives.

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