Focuh

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

The description adds no behavioral context beyond what the annotations already imply. It does not disclose anything about side effects, duplicate handling, return behavior, or prerequisites for creation. Annotations indicate it is a write operation, but the description itself provides no additional transparency.

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?

One sentence with no filler. It front-loads the action and resource, then lists the relevant scope and optional fields efficiently.

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 plus schema is enough to make a syntactically valid call: required title and horizon are in the schema, and horizon has an enum. However, the meaning of lever and bottleneckNote, and the expected return value, are left unspecified, making it merely 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?

Schema description coverage is 0%, so the description must compensate, but it only mentions optional bottleneckNote and lever and does not explain their meaning. It also omits title from the description, leaving required-parameter semantics entirely 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?

States a specific verb ('Create') and resource ('a goal'), plus the target container ('in a horizon') and the key optional fields. This clearly distinguishes it from siblings like create_tasks and update_goal.

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 this when creating a goal. However, it does not explicitly mention when to prefer this over create_tasks or how it differs from update_goal, so guidance remains implicit rather than explicit.

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?

Discloses non-obvious default behavior: omitted dates default to today and duration defaults to 30 minutes. It also clarifies that nested subtasks are optional, which is useful beyond the raw schema. Annotations already indicate this is a non-read-only, non-idempotent mutation, so the description adds appropriate context without contradicting them.

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 short, efficient sentences. The primary action is front-loaded, and the defaults are packed into a compact, scannable phrase with no filler or redundant explanation.

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 one-parameter create tool with a fully described schema, the description covers the key behavioral defaults and nested-task capability. A return-value description would be nice, but its absence is not a major gap for a creation endpoint whose schema already documents all inputs and annotations cover safety properties.

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 100% schema description coverage, the baseline is 3, but the description adds value by specifying defaults for date and estimatedMinutes and by highlighting the optional subtasks array. The mapping is slightly implicit, but the schema's 'Date' and 'Minutes' descriptions make it reasonably clear.

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 concrete operation and resource ('Create tasks') and adds the meaningful scope 'each with optional nested subtasks,' which distinguishes it from sibling tools like update_tasks, delete_tasks, and get_tasks. The defaults also add specificity beyond a mere restatement of the title.

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?

There is no guidance about when to use this tool versus alternatives such as update_tasks or delete_tasks. The name implies creation, but the description does not state conditions, exclusions, or relationships to 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?

Annotations already mark the tool as destructive and idempotent; the description goes further by disclosing the precise scope of destruction—only the goal is deleted, linked tasks are unlinked and kept. 'Never deleted' adds strong value beyond the destructiveHint annotation.

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 short sentences with the main action first and the critical side effect second. Every word earns its place; 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?

Covers the core action and the key side effect; idempotentHint covers repeated deletes. However, it does not mention whether associated subtasks or other linked entities are affected, and with no output schema the return/error behavior is left implicit.

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 0% for the single id parameter, so the description must compensate. 'by id' correctly maps the parameter to the goal identifier, which is sufficient for a one-parameter tool; no extra format or source guidance is needed given the schema's maxLength.

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 ('Delete a goal by id') and clarifies the key boundary relative to delete_tasks: linked tasks are kept and unlinked, never deleted. This distinguishes the tool from 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 implies when to use this tool (when you want to remove a goal while preserving its tasks) but does not explicitly state when not to use it or name alternatives. The side-effect sentence offers implicit guidance but no exclusions.

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 the tool as destructive and not read-only. The description adds valuable behavioral context beyond that by revealing cascade deletion ('Subtasks go too') and clarifying the bulk scope of each deletion mode, which the schema alone would not convey.

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 short sentences with no filler. The core action and selection modes are front-loaded, and the cascade behavior is stated as a separate, impactful note. Every 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?

For a destructive tool with three modes, no output schema, and annotations covering idempotence and destructiveness, the description covers the key usage surface and a critical side effect. The main gap is that it does not explicitly say whether the three modes are mutually exclusive or what happens when no parameter is provided, especially since there are no required parameters.

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 0% schema description coverage, the description is the only semantic documentation for the parameters. It maps 'tasks' to references, 'date' to deleting every task on a date, and 'filter' to deleting all completed tasks. It does not explain mutual exclusivity or exact formats, but it gives each parameter a concrete role.

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 ('Delete') and resource ('tasks'), then enumerates three distinct selection modes: by ref, by date, and completed. This clearly separates it from siblings like delete_goal and makes the tool's scope immediately actionable.

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 intended use is implied: delete tasks when tasks need removal. However, there is no explicit mention of when not to use it or how it compares to alternatives such as update_tasks, and the description relies on the tool name and verb to convey when it should be selected.

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 establish that this tool is read-only, idempotent, and non-destructive. The description adds that it aggregates events and both scheduled and unscheduled tasks, but it leaves ambiguous how 'unscheduled tasks' map to a specific date and what happens when the optional date is omitted.

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 short sentences, front-loaded with the tool's content and followed by practical scheduling guidance. Every word earns its place with no filler or 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 one-parameter read-only tool this is nearly adequate, but there is no output schema and the description only provides a high-level return summary. It does not clarify the date format, optional date behavior, or how unscheduled tasks are represented, leaving an agent to infer these important operational details.

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?

There is one parameter, 'date', with no schema description and 0% schema description coverage. The description only repeats 'for a date' and does not specify the expected date format, optionality, or default behavior, so it fails to compensate for the schema's silence.

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 resource ('calendar') and its content ('events + scheduled/unscheduled tasks') for a date. It is specific enough to distinguish from task-only siblings like get_tasks, though it does not explicitly name a sibling alternative.

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?

'Check before scheduling' provides an explicit when-to-use directive, and the aggregate listing of events and tasks is the right context for scheduling decisions. It stops short of 5 because it does not mention when not to use it or name an 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds the 'today/week' scoping of the returned focus minutes, which is a useful behavioral detail about what time range the stats cover. It does not disclose how streak is computed or whether the response shape is a summary object, but given annotation coverage, a 3 is appropriate.

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 short, front-loaded list of returned data with no filler words. It is concise but is a sentence fragment lacking a verb, so it is not as polished as a fully structured sentence. Still, every 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?

For a zero-parameter, read-only stats endpoint with a clear annotation profile, the description is largely complete: it names the metrics returned. The lack of an output schema is partially offset by the list of data points. It does not give units or date format details, but for this simple tool that is a minor 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?

The tool has zero parameters, so there are no input semantics for the description to explain. Per the rubric baseline, 0 parameters earns a 4. No further parameter information is 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 title 'Focus Statistics' and the description make it clear that this tool returns focus-related metrics. The description enumerates the specific data points (focus minutes, streak, completion rates), which distinguishes it from sibling tools like get_tasks or get_journal. However, it lacks an explicit verb such as 'retrieves' or 'returns', so it falls short of a purpose statement that names the action.

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 no guidance on when to use this tool versus alternatives. It doesn't state what types of queries are appropriate or reference any sibling tools. The only hint is the name and content, which implies this is the default for focus stats, but no explicit usage context or exclusions are given.

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 only needs to add context. It adds horizon scoping and the app-view equivalence, but it does not disclose defaults for the optional parameters, how status interacts with horizon, or the response shape. There is no contradiction with 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?

One concise, front-loaded sentence that names the resource and scope before adding the app-view clarification. Every phrase earns its place, with no repetition or fluff.

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 read-only list tool with two optional enum parameters, the description plus schema is mostly usable. However, with no output schema and zero schema description coverage, the missing status semantics and lack of default-filter behavior leave meaningful ambiguity for an agent deciding how to 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 0%, so the description must compensate. It explains the horizon enum by listing week/month/year/decade, but it leaves status (active/completed/all) entirely unexplained, including its meaning and relationship to horizon. This is only partial compensation for the missing schema descriptions.

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 resource (goals) and scope (horizon: week/month/year/decade), and ties the tool to the app's Goals view, distinguishing it from task/calendar/journal tools. It lacks an explicit verb, but the title 'View Goals' and read-only annotations make the operation clear. It does not explicitly call out sibling goal tools, but the resource and view framing are sufficient.

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 phrase 'exactly what the app's Goals view shows' provides clear context for when this read-only retrieval tool is appropriate. It does not explicitly state when to avoid it or name alternatives like create_goal/update_goal, but the read-only nature and sibling set make the intended usage reasonably apparent.

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 non-destructive behavior, so the description does not need to restate those. It adds a useful behavioral caution: "Preserve ^task markers when writing back," which tells the agent that journal content may contain markers that must survive round-trips. This goes beyond the structured 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 very concise and front-loaded with the core purpose. The additional warning about ^task markers is short and adds important behavioral context without unnecessary elaboration.

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 read operation with strong annotations, the description covers the basic action and warns about an important data quirk. However, there is no output schema, and the description does not explain what the response contains, how multiple dates are returned, or how the date parameter behaves. This leaves some gaps for an agent trying to use the 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?

Schema description coverage is 0%, and the description does not meaningfully explain the optional date parameter. The phrase "daily journal and recent dates" hints at date-based behavior but does not clarify the expected format, the effect of omitting the parameter, or the exact scope of "recent dates." The description fails to compensate for the missing 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 states a specific action and resource: "Read a daily journal and recent dates." This clearly identifies what the tool does and distinguishes it from sibling tools like write_journal. However, it does not explicitly differentiate from other get_* tools or clarify what "recent dates" means.

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 tool is for reading journal content, and the readOnly annotation reinforces that. It does not explicitly say when to prefer it over alternatives, nor does it mention write_journal as the counterpart for modifications. Usage context is present but only implied.

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 safety is covered. The description adds useful behavioral context beyond those annotations by defining what loops are (undated intentions), enumerating the four buckets, and noting the ordering dependency on pull_loops.

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 short sentences with no filler. The core definition is front-loaded, and the sequencing guidance appears immediately after, making it easy to scan.

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, idempotent tool with no output schema, the description provides enough—the entity definition, bucket taxonomy, and the key relationship with pull_loops. Nothing critical is missing for an agent to 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?

The tool has zero parameters and schema description coverage is 100%, so no parameter documentation is needed. Per rubric, 0 params gets a baseline of 4; the description adds nothing about parameters because there are none.

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 the resource ('undated intentions in 4 buckets') and distinguishes it from pull_loops by saying 'Call before pull_loops,' but it never explicitly states the retrieval action—'View Loops' in the title supplies that verb. Overall, an agent can tell this is a read-style tool distinct from its 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 description gives explicit sequencing context: 'Call before pull_loops.' This tells the agent when in a workflow this tool belongs, though it does not explain when not to use it or compare against other read tools like get_tasks.

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 (readOnlyHint=true, idempotentHint=true, destructiveHint=false), lowering the burden on the description. The description adds genuine behavioral value by disclosing that the return value is a set of ids that can be fed back as refs to other tools, which an agent needs to know when chaining calls. It does not contradict 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?

Two sentences with zero waste. The primary function is front-loaded in the first sentence, and the second sentence communicates the output format without padding. Every 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?

For a single-parameter read-only tool with strong annotation coverage, this is nearly complete: an agent needs only a ref and knows it will get ref-usable ids back. The remaining gaps are minor but real — it does not specify whether 'subtasks' means only direct children or includes nested descendants, nor does it cover ordering or empty-result behavior. These do not block correct 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 coverage is 100% and the ref parameter is already documented as accepting 'Task id, #N, or title', so the baseline is 3. The description adds semantic value above the baseline by linking the output to the parameter: the returned ids are specifically 'usable as refs', meaning they satisfy this same parameter format in downstream calls. This creates a useful input-output contract.

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 ('List') with a clear resource ('subtasks of a parent'), and the 'of a parent' scoping distinguishes this from the sibling get_tasks tool. The second sentence adds an output contract (ids usable as refs) that further defines the tool's role. This is unambiguous and informative.

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 usage context is implied by the purpose: call this when you have a parent task and want its subtasks. However, there is no explicit guidance about alternatives, such as using get_tasks to list all tasks or reorder_subtasks when restructuring is needed. No exclusions or when-not-to-use conditions are stated.

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 establish readOnly, idempotent, and non-destructive behavior. The description adds useful behavioral context by scoping results to today/tomorrow and noting that the returned refs are intended to be used afterward, which goes beyond the structured 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?

Two short sentences, both information-dense and front-loaded. The first identifies the resource and fields; the second states its intended role in the workflow. 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?

For a zero-parameter, read-only list tool with strong annotations, the description supplies the key missing context: what data comes back and why the agent should call it. An output schema is absent, but the description names the essential fields, making the tool callable and understandable.

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?

There are no parameters, so the description bears no burden for parameter documentation; the schema already covers everything. The description appropriately focuses on return content rather than inputs, matching the zero-parameter baseline.

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 today/tomorrow tasks with id, date, and priority, which is a specific resource and scope. It also indicates a bootstrap role ('Call first to get refs'), distinguishing it from task mutation and subtask tools without opening 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?

'Call first to get refs' provides an explicit when-to-use instruction, positioning this as an initial retrieval step. It does not name alternatives or exclusions, but with zero parameters and a clear read-only scope, the context is sufficient.

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 annotations already provide idempotentHint and destructiveHint, and the description adds useful context by stating that loops are copied rather than moved and that linked tasks are created. It reinforces the side-effect boundary without contradicting 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?

The description is two short sentences that front-load the core operation and place the idempotency caveat at the end. Every phrase earns its place with 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 structurally simple two-parameter tool, the core behavior, idempotency, and non-destructive nature are sufficiently covered. It could be slightly more complete by addressing the optional date default and naming the alternative tool to use instead, but those are minor 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?

The description conceptually maps loops as the items being copied and date as the destination, which adds meaning beyond the bare schema. However, with 0% schema description coverage, it leaves gaps such as date format, why date is optional, and how loop identifiers are expected.

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 and resource: 'Copy loops onto a date as linked tasks.' It also clarifies the key distinction that 'each loop stays in Loops,' separating this from move-style or purely task-creation 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 usage is implied: use this to pull existing loops onto a date rather than creating tasks or loops from scratch. However, no explicit alternatives are named and there is no when-not-to-use guidance relative to siblings like create_tasks or get_loops.

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?

Beyond the annotations (mutating, idempotent, non-destructive), the description discloses that the order array must be the complete new order and must include every subtask exactly once. This is useful behavioral context about replacement semantics that the annotations alone do not convey.

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 short sentences deliver the core action and the most critical constraint. Every clause earns its place, and the key caveat about completeness is front-loaded in the second sentence.

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 reorder operation, the description is largely complete: it names the action, the resource, and the key constraint on the order array. It does not discuss error behavior or what happens if the array is incomplete, but those are minor gaps given the annotations and simple parameter set.

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 only 50%, with the 'order' parameter lacking a description. The description compensates by explaining the crucial semantics of 'order': it must be complete and each item appears once. The 'ref' parameter is only documented by the schema, but the schema description for it is adequate.

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 a specific action ('Reorder') applied to a specific resource ('a parent's subtasks'), distinguishing it from sibling tools like get_subtasks or update_tasks. The phrase 'complete new order, every one once' further clarifies the intended operation.

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 when to use the tool: when a user wants to reorder a parent's subtasks. However, it does not explicitly mention alternatives or situations where this tool should not be used, such as when only partially modifying subtask order might be expected.

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 this as a non-read-only, idempotent, non-destructive operation, so the description's burden is reduced. It adds useful behavioral detail with 'horizon (moves section)', but does not disclose permissions or other side effects beyond that.

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 filler. It front-loads the action and immediately enumerates the relevant fields.

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 strong annotations, the description is mostly adequate, but the lack of an output schema and 0% parameter documentation leaves some ambiguity around return behavior and the meaning of less obvious fields. It is not fully self-sufficient but covers the core operation.

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's field list is the primary documentation of what is updatable. It adds one semantic detail (horizon moves section) but does not explain domain-specific fields like lever or bottleneckNote, nor the meaning of enum values for status and horizon.

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 ('Update') and resource ('goal fields') and enumerates all editable fields, which clearly distinguishes it from siblings like update_tasks and create_goal. It is immediately clear what the tool operates on and what can be changed.

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 no explicit guidance about when to use this tool versus alternatives such as create_goal or update_tasks. The intended usage is implied by the name and field list, but no exclusions or alternative routing are provided.

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=false, idempotentHint=true, and destructiveHint=false, so the mutation and safety profile is known and the description does not contradict it. The parenthetical 'date (moves the day)' adds a minor semantic clarification, but the description does not explain behavior for missing refs, idempotent application, or side effects. It is adequate given annotation coverage but adds little extra 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 front-loaded sentence with no filler. It is appropriately brief for a straightforward update tool, though terms like 'estimate' and 'done' are informal and slightly reduce precision.

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 schema covers all parameters and annotations supply idempotency and non-destructiveness hints, but the description is thin for a tool with 10 editable fields and no output schema. It does not state that updates are keyed by ref, that goalId and loopBucket are also changeable, what happens to omitted fields, or what the tool returns. Core update semantics are clear, but meaningful gaps remain.

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 description adds useful aliases like 'estimate' for estimatedMinutes, 'done' for completed, and 'time slot' for start/end times, and clarifies that date moves the day. However, it does not mention ref, goalId, or loopBucket, and the schema descriptions themselves are terse, so parameter meaning is only mildly enhanced.

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 clear imperative verb ('Change') and resource ('tasks'), then enumerates the editable attributes: date, priority, title, estimate, done, time slot. This distinguishes it from create/delete/get siblings by verb, though it omits goalId and loopBucket and does not explicitly contrast with update_goal.

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?

No usage guidance is provided. The description does not state when to use update_tasks versus create_tasks or delete_tasks, does not mention that only existing tasks are updated, and gives no prerequisites, exclusions, or alternative routing. The verb 'Change' provides weak implicit context only.

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 discloses meaningful behavior by warning to preserve ^task markers and read before replacing. However, the annotations declare destructiveHint=false while the description's replace mode and preservation warning indicate destructive data-loss risk, which is an annotation contradiction that leaves an agent with conflicting signals.

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 no filler; the core action is front-loaded and the second sentence adds an important behavioral caveat. Every word carries weight.

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 mutation tool with no output schema and sparse annotations, the description is minimally viable but incomplete: it does not specify the mode default, date format, response behavior, or how to preserve task markers beyond a short instruction. An agent can invoke it correctly for basic cases but may guess on edge cases.

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 0% schema description coverage, the description provides some parameter meaning: it explains the mode choices (append/replace), implies content is journal text, and adds the ^task marker requirement. Still, date semantics and content format are not explained, so it only partially compensates for the schema 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 uses a specific verb phrase 'Append or replace a journal,' naming the exact action and resource. It also signals that this is the write counterpart to tools like get_journal, distinguishing it from the read and goal/task 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?

It clearly implies use when the agent needs to create or modify a journal by appending or replacing content. It lacks an explicit exclusion or pointer to get_journal as the alternative, though the instruction to 'Read before replacing' strongly suggests the prerequisite read path.

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