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

With no annotations, the description carries the transparency burden. It supplements the schema by explaining that water_every_days is the watering interval in days, and that using the default is acceptable when unsure, with a later correction path. This goes beyond the raw schema and is useful 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 a single, focused sentence that front-loads the purpose and immediately provides a helpful parameter tip. No wasted words, clear and efficient.

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?

The tool has 5 parameters and no annotations, but the description only sheds light on one parameter. It covers the core purpose and the default behavior for water_every_days, but leaves other parameters, return values, and error handling undocumented. Given the simplicity of a create operation and the existence of an output schema, this is partially complete but with notable gaps.

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 0%, so the description must compensate. However, it only explains water_every_days, leaving name, species, location, and acquired_on without additional semantic meaning beyond their names. The watering interval guidance is helpful, but most parameters are not elaborated.

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 action: 'Registers a new plant' (새 식물을 등록한다). The verb 'register' and resource 'plant' are specific, and it distinguishes from siblings like remove_plant, update_plant, and get_plant.

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 practical usage guidance for the water_every_days parameter: if unknown, use the default 7 and adjust later with update_plant. This explicitly names an alternative tool for adjustments, though it doesn't broadly discuss when to use this tool versus other plant-related 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 are provided, so the description carries the full burden. It only restates the function ('returns summary') without disclosing side effects, return format, error behavior, or any operational nuances. For a simple getter, this is minimal 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?

The description is a single efficient sentence with no wasted words. However, it is under-specified, which limits the value of its brevity.

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 optional 'as_of' parameter, no annotation coverage, and no parameter explanations, the description is incomplete. The existence of an output schema helps, but the description fails to guide proper invocation or parameter usage.

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 0%, and the description does not explain either parameter. 'name' is inferable from context, but 'as_of' is completely undocumented, leaving a significant gap for the agent.

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 current status summary for a single plant. This is a specific verb+resource combination that differentiates it from siblings like list_plants (all plants) and plant_history (historical data).

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 usage when one wants the current status of a single plant. However, it provides no explicit exclusions or comparisons to alternatives like plant_history or list_plants, leaving some inference required.

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?

With no annotations provided, the description carries the full burden. It discloses the key behavior: returns all plants with watering-relevant fields and the as_of calculation effect. However, it does not mention return format, pagination, or any potential performance implications, which would be useful for a full list 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?

A single, well-structured sentence states the primary purpose first, followed by the optional parameter behavior. No filler or redundancy. Front-loaded and efficient.

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 tool's low parameter count and presence of an output schema, the description sufficiently covers the essential behavior. It explains what data is returned and how the optional date parameter affects computation. Could be marginally improved by referencing the filtered sibling tool, but is otherwise complete.

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 schema has one parameter (as_of) with no description (0% coverage). The description compensates by explicitly explaining its meaning: if provided, calculations are based on that date. This adds meaningful context beyond the schema's bare type definition.

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: returning all registered plants with computed fields (last watered, elapsed days, next scheduled date). It distinguishes from sibling tools like get_plant (single plant) and plants_needing_water (filtered list) by emphasizing 'all registered plants,' though it does not explicitly name these alternatives.

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 implied: use when you need a comprehensive list of all plants with watering schedule details. The as_of parameter is explained for date-relative calculations. However, there is no explicit guidance on when to prefer this over siblings like plants_needing_water, or when not to use it.

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?

With no annotations, the description must carry the behavioral burden. It indicates a write operation ('기록한다' = records) and clarifies that observations are left as-is, but does not disclose return behavior, permissions, or mutability. It is not misleading, but incomplete.

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 two sentences, front-loaded with the purpose and followed by clarifying examples. No wasted words; every part 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?

While the output schema covers return values, the description lacks essential context about the 'name' parameter referring to an existing plant and when to use this vs log_watering. It is adequate for a simple note logger but has clear gaps in the broader tool ecosystem.

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 0%, and the description only provides context for the 'note' parameter via examples. The 'name' parameter is not explained as the plant identifier, and 'noted_on' is completely unaddressed. The description fails to compensate for the lack of schema documentation.

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 records plant state changes, with explicit examples of observation content. It distinguishes itself from sibling tools like log_watering by focusing on observational notes rather than watering events.

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 implied through the examples and context (plant observations vs watering), but no explicit when-to-use or alternative tool references are provided. The description lacks direct guidance on when to choose this over log_watering.

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?

With no annotations provided, the description adds behavior details: the date defaults to today if omitted, and amount accepts free-form memos. It does not disclose potential side effects like updating plant status or require an existing plant, but it conveys the core behavior.

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 three short, front-loaded sentences, each adding useful information. No redundant or filler content.

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 logging tool with an output schema, the description covers the main purpose, key parameters, and default behavior. It omits any side effects or error conditions, but the tool is straightforward and the output schema covers return values.

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 description explains the watered_on parameter default and the amount parameter format ('흠뻑', '200ml'), but leaves the required name parameter unexplained. With 0% schema coverage, this partial compensation is helpful but incomplete.

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 logs watering events with a specific verb ('records') and resource (watering). It is clear but doesn't explicitly differentiate from sibling tools like log_note, though the domain is specific 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?

The description implies the usage context (logging watering) but provides no explicit guidance on when to choose this over alternatives. It mentions behavioral details like the default date but not any exclusions or prerequisites.

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 are provided, so the description carries the burden. It discloses the return format (timeline, latest-first) and content (watering/observation records). It does not explicitly state read-only, but 'returns' implies a safe read operation, which is sufficient for this simple 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?

The description is a single, focused sentence that immediately states the tool's purpose and ordering. No unnecessary words or repetition.

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 tool type and presence of an output schema, the description covers the core behavior well. However, the lack of parameter explanations and explicit usage guidance leaves minor gaps, but the description is not misleading.

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 no parameter descriptions (0% coverage), and the description does not explain 'name' or 'limit'. The description only implies that 'name' refers to a plant, but adds no detail about the limit parameter or their semantics. This is a clear gap.

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 watering/observation records as a latest-first timeline. The verb 'returns' and resource 'plant's records' are specific, and it distinguishes itself from sibling tools like get_plant and list_plants by focusing on historical records.

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 use for viewing a plant's history, with clear context from the content type and ordering. It does not explicitly mention alternatives or exclusions, but the purpose is evident from the tool's name and siblings.

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?

With no annotations, the description must carry the burden of behavioral disclosure. It mentions the sort order (overdue amount) and that it returns only needing-water plants, but does not state its read-only nature explicitly or any other side effects. Some behavioral context is provided, but more could be said about the time aspect (as_of).

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 two concise sentences, front-loaded with the main action ('returns only plants needing water') and then provides additional details (sorting and usage example). No wasted words.

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 there is an output schema and the tool is a simple query, the description covers the core behavior. However, the unexplained 'as_of' parameter leaves the input semantics incomplete. It could also mention that it is read-only, but overall it's mostly adequate.

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 schema has one optional parameter 'as_of' with zero coverage (no description). The tool description does not explain what 'as_of' does or how it affects the results, providing no added meaning beyond the type. This is a significant gap.

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 clearly states the tool returns only plants needing water, sorted by overdue degree. This distinguishes it from siblings like list_plants (which would list all plants), and the example query clarifies its purpose.

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 use case is given: 'Use for questions like Who's thirsty today?' This tells the agent when to invoke this tool. However, it does not explicitly mention when not to use it or contrast with list_plants, so it misses a bit of exclusion 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?

With no annotations provided, the description carries the full burden. It discloses that the operation is irreversible, deletes not just the plant but all associated records, and requires confirmation. This goes beyond a generic 'deletes a plant' and gives critical 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?

Two sentences, no fluff. The first sentence states the action, the second provides the critical condition. Each word 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?

The description fully covers the tool's behavior, including its scope, irreversibility, and prerequisites. Since an output schema exists, return values need not be described. It is complete for the tool's complexity.

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 0%, so the description must compensate. It clarifies that 'name' refers to the plant to be deleted, and it explicitly states the 'confirm' parameter must be set to True, explaining its purpose and necessity.

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 '삭제한다' (deletes) and the resource '식물과 그에 딸린 모든 기록' (plant and all associated records). This distinguishes it from sibling tools like get_plant, update_plant, and list_plants.

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 explicitly tells the agent when to use this tool: only after receiving user confirmation, and it must be called with confirm=True. This provides a clear condition and implies when not to use it (without confirmation).

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose the important partial-update behavior ('only passed items change') and implies the plant must already exist via '등록된 식물'. However, it does not describe error conditions, return behavior, or side effects, leaving some transparency gaps 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?

The description consists of two short sentences, front-loaded with the verb and resource. Every word is meaningful, and the partial-update note is delivered efficiently without 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?

For a simple update tool with an output schema present, the description adequately covers the core behavior and the key nuance of partial updates. It doesn't need to explain return values since the output schema exists, and the sibling list provides context. Minor gaps like error handling are acceptable at this complexity level.

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 schema itself has no descriptions for its four parameters, and the context signals indicate 0% schema description coverage. The description compensates by explicitly mapping species, location, and water_every_days to their Korean terms, and the partial-update note clarifies how omitted parameters behave. However, the 'name' parameter's role as an identifier is only implicit.

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 a specific verb ('수정한다' meaning 'modifies') and identifies the resource ('등록된 식물' meaning 'registered plant') along with the specific fields (species, location, watering interval). This clearly distinguishes the tool from siblings like add_plant and remove_plant, and the partial-update note further clarifies its unique function.

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 makes it clear that this tool is for updating existing registered plants and that only passed fields are changed, which is a key usage guideline. However, it does not explicitly mention when not to use it or name alternatives, though the tool name and sibling list imply the distinction.

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