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

Beyond the readOnly and non-destructive annotations, the description discloses several non-obvious behaviors: missing punches are suppressed if the record already has that start/end time, unknown break time affects the 12-hour threshold logic, overnight shifts are recognized, and leave/requests are invisible via the API so 'no punches' may be a day off. These details materially affect how an agent interprets results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loads the issue list, then moves to caveats and date constraints. It is longer than typical, but the length is justified by the number of distinct checks and the need to explain suppression logic and date defaults; it could be more scannable but contains no obvious filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only checker with no output schema, the description is complete enough: it enumerates the issue categories, default date range, max span, overnight handling, and interpretation caveats such as invisible leave requests. An agent has what it needs to call the tool correctly and interpret the likely results.

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%, so the parameters are already documented, but the description adds meaning beyond the schema: it specifies the default range as the 1st of this month through yesterday (with the 1st rolling to the previous month) and states a maximum span of 93 days. This clarifies edge-case date behavior not present in the input schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Check your own punches and working records for issues') and enumerates the exact issue types it detects, from missing punches to rest intervals. This clearly distinguishes it from siblings like get_working_records and get_alerts, which serve different purposes.

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 by the issue-checking context, and the description gives useful default date range and max-days constraints. However, it does not explicitly state when to use this versus alternatives such as get_working_records or get_alerts, nor does it name 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?

Annotations already flag destructiveHint=true and idempotentHint=true, so the description's job is to add blast-radius detail, which it does well: omitting taskId wipes ALL tasks of the project for that day. It also discloses a precondition (closed/fixed days reject changes) that annotations cannot express. It stops short of saying whether deletes are recoverable or what a failure returns.

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, zero filler, and the critical bulk-delete warning is front-loaded immediately after the purpose statement. The precondition clause is correctly placed last as a secondary constraint.

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 three-parameter mutation with no output schema, the description covers purpose, blast radius, and blocking preconditions. Only the response/error shape and recoverability are unaddressed, which are minor given the annotation coverage.

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 67%, and the description adds the most important semantic beyond the schema: the omitted-taskId case is a bulk delete across the whole project-day, not a no-op. projectId has no schema description but the description ties it to the day/task scope. Date format details remain in 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 and resource ("Delete your own man-hours") plus the exact granularity of one day and one project, which cleanly separates it from siblings like save_manhours and get_manhours. The scope qualifier "your own" tells the agent whose data is affected.

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?

Gives clear operative context: what happens when taskId is omitted, and that closed (締め) or fixed (確定) days cannot be changed. It does not explicitly name save_manhours as the alternative for corrections, but the usage conditions are unambiguous.

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, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds that results are scoped to the calling user, but says nothing about volume, ordering, or freshness of alerts, which would matter for a list-style read.

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 front-loaded sentence: verb + resource + scope first, then the alert-type examples and the optional filter. The bilingual parentheticals are long but carry domain meaning for Japanese HR terms; little else is wasted.

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?

Safety is covered by annotations and the only parameter by the schema, but there is no output schema and the description never indicates what an alert record contains or how results are ordered. That leaves a real gap for an agent consuming the response.

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 single month parameter already carries a YYYY-MM pattern and description. The description's 'Optionally filter by month' merely confirms optionality, adding no format or edge-case detail beyond the schema — baseline 3 applies.

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 gives a specific verb (Get) and resource (your own attendance alerts) and enumerates the concrete alert types (missing punches, suspected absence, lateness, 36 agreement, etc.), which is far more specific than the title alone. It stops short of differentiating from the nearby sibling check_attendance_issues, so an agent must infer the boundary.

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?

'Get your own' and 'Optionally filter by month' imply the scope and the one optional narrowing, but there is no explicit when-to-use vs check_attendance_issues or get_today_status, and no exclusions. Usage is inferable rather than 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 declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds real operational context on top: the 93-day maximum range, the default date window, and the fact that closed (締め) / fixed (確定) days are locked. The return shape (per day/project/task, in minutes, names included) is also disclosed. It stops short of stating pagination or whether results are truncated at the 93-day cap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short, front-loaded sentences with no filler; the resource and output shape come first, constraints after. The closed/fixed-day sentence is slightly tangential for a read-only tool and reads as a caveat aimed at a write workflow, which costs a point.

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 only two fully documented optional parameters, no output schema, and annotations covering the safety profile, the description supplies everything an agent needs: default window, hard range limit, returned dimensions and units, and the immutability caveat for closed/fixed days.

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%, so baseline is 3; the description earns an extra point by adding the 93-day maximum span, a constraint the schema does not encode. The "Defaults to this month" line reinforces but largely restates the schema's default descriptions for `from`/`to`.

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?

Specific verb plus resource ("Get your own man-hour records (工数)"), with the granularity stated (per day, project, task) and the unit of measure (minutes). It is immediately distinguishable from save_manhours/delete_manhours and from get_working_records, and the "your own" scope rules out multi-user lookup.

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 rather than stated: "your own" bounds the scope and "Defaults to this month" tells the agent what happens if it omits dates. But no alternative is named (e.g. summarize_working_hours for aggregates, get_working_records for a different record type) and no when-not condition is 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 establish that this is a read-only, non-destructive operation. The description adds useful behavioral context by listing what is returned, including role values and Japan-time date information, though it does not discuss permissions, error behavior, or response shape beyond the field list.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: it states the core action first, then the returned fields and role values. Every sentence adds useful information without repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, read-only tool with annotations covering safety, the description is complete. Since there is no output schema, it correctly explains the returned fields and includes the relevant role and timezone 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?

The tool takes no parameters, so there are no parameter semantics to document. The baseline for a zero-parameter tool is 4, and the description does not need to compensate for schema gaps.

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: 'Get the signed-in employee's own profile.' It further clarifies the exact contents (staff ID, name, organization, permission role) and distinguishes the resource from siblings such as projects, status, stamps, and work 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 that the tool is used to retrieve the current user's profile, but it gives no explicit when-to-use guidance, no exclusions, and no comparison to sibling tools such as get_today_status or get_my_projects.

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, destructiveHint=false and openWorldHint=true, so the safety profile is covered structurally. The description adds only that results carry project names and IDs suitable for man-hours; it says nothing about volume, ordering, or whether an empty membership list is possible.

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, no filler, with the scope constraint and the actionable follow-up use front-loaded. Every phrase 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?

With no parameters and no output schema, the description carries the burden of describing the return, and it does so at a basic level (project names plus projectIds). Slightly more detail on the returned shape would make it fully self-sufficient, but nothing essential for correct invocation 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 takes zero parameters, so there is nothing to disambiguate and the baseline of 4 applies. The description correctly does not waste words on inputs.

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 and resource ('List the projects') with a clear scope restriction ('you are a member of'), which implicitly separates it from the sibling list_projects. It also notes the returned names, so an agent knows what comes back. It stops short of explicitly naming the sibling it differs from.

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?

'Use these projectIds for man-hours' gives a downstream purpose, implying this is the lookup step before get_manhours/save_manhours. However, it never names an alternative tool or states an exclusion, so the agent must infer that list_projects is the wrong choice for member-scoped project IDs.

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, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: automatic chunked fetching for long periods, a hard 366-day ceiling, and default omission of location and IP fields — all of which affect how results should be interpreted.

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 dense paragraph, front-loaded with the core purpose and followed by behavior constraints in order of importance. The parenthetical Japanese terms add length but earn their place for matching against Japanese source data; only minor trimming is possible.

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-only, 2-param date-range tool with no output schema, the description covers what is returned (stamp types), how far back it can go (366 days, chunked internally), and what is filtered out (location, IP). An agent has everything needed to call it correctly and interpret the response scope.

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%, so both parameters are already documented with format patterns and defaults, which sets the baseline at 3. The description reinforces 'for a period', the today default, and the 366-day maximum, but adds no new semantics about the from/to relationship beyond what the schema states.

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+resource ('Get your own punch history') and immediately enumerates the stamp categories returned (clock in/out, direct in/out, break start/end) with Japanese labels. An agent can distinguish this from get_today_status or get_working_records by the explicit 'for a period' framing and the 'your own' scoping.

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 rather than stated: 'Defaults to today' hints that the tool is for the current day when no args are given, and the 366-day cap signals planning considerations, but no sibling is named as an alternative or complement. Nothing tells the agent when to prefer get_today_status or get_working_records instead.

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 read-only, non-destructive operation, so the safety profile is covered. The description adds meaningful behavior beyond annotations by specifying Japan-time status values and that returned work time excludes breaks, along with break time and today's punches.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: it leads with the purpose, then the status values, then the returned data, then the usage cue. Every clause adds useful information without 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?

With no parameters and no output schema, the description carries the return-value burden and does so adequately by naming the possible statuses and the data returned. The read-only safety profile is already covered by annotations.

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 takes zero parameters, so there is no parameter semantics to explain. The schema is empty and the description correctly does not invent parameter guidance.

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: getting today's work status in Japan time. It also enumerates the exact status values and returned fields, so an agent can distinguish it from siblings like punch or get_working_records without opening the schema.

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 says to use this before punching, which gives a clear invocation context. It does not name exclusions or alternative tools beyond that, so it falls short of full when/when-not 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?

Annotations only say readOnly/openWorld; the description adds substantial behavior the agent could not otherwise know: the API omits actual working minutes and breaks, actual minutes equal elapsed start-to-end with breaks included, break time is unknown, there is no overtime field, long ranges are auto-split into 31-day requests, and the hard cap is 366 days. These are exactly the caveats that prevent misinterpreting results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with what is returned, then the interpretation caveat, then defaults and routing. Every sentence carries information the agent needs to call and interpret the tool correctly; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description enumerates the return fields and explicitly flags the absent ones (working minutes, breaks, overtime), which is the critical completeness gap for this tool. Combined with the range limits and default window, an agent can call it and interpret the response without further help.

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%, so the two date parameters and their defaults are already documented; the description reinforces the default window and adds constraints the schema lacks (automatic 31-day chunking, 366-day maximum). It stops short of format edge cases (inclusive/exclusive handling is only in the schema), so it is an enhancement rather than a replacement.

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+resource ('Get your own daily working records') and enumerates the returned fields (day category, start/end time, punch times), so the agent knows exactly what data comes back. It is clearly distinguishable from get_today_status (single day) and summarize_working_hours (aggregates).

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?

Explicitly routes aggregation/overtime needs to summarize_working_hours and states the default date window, giving the agent clear context for when this tool applies. It does not address the remaining adjacent siblings (get_stamps, get_today_status, punch) or when a narrower call would be preferable, so it stops short of full when/when-not coverage.

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, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds that filtering is optional and that projectId is the join key for other tools, but says nothing about pagination, result size, or ordering — notable given openWorldHint=true.

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 tight sentences: identity and scope first, filters second, downstream usage last. The Japanese glosses (プロジェクト, 工数) are the only extra tokens and they disambiguate domain terms.

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?

There is no output schema, so the description should convey what a returned project record contains (id, name, code, active period). It implies projectId but never states the returned fields or result ordering, which is a real gap for an agent constructing follow-up calls.

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%, so both parameters are already fully documented. The description only restates them at a high level ("filter by name/code" and "date the project is active on") and adds the useful but minor point that both are optional. Baseline 3 applies.

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 and resource ("List the company's projects") and scopes it to man-hour tracking, which an agent can distinguish from task/attendance siblings. It does not explicitly contrast with the closest sibling, get_my_projects, leaving the company-wide vs. personal scope difference implicit.

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?

Gives clear downstream routing — "Use the projectId with list_tasks and save_manhours" — which tells the agent why it would call this first. It stops short of explicit exclusions (e.g., when to prefer get_my_projects over this list).

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the default result filter (finished tasks hidden) and that estimated time is in minutes, which is genuine context beyond the annotations. No contradiction with the read-only hint.

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?

Three short sentences, front-loaded with the action and followed by the two behavioral facts an agent needs. The includeFinished clause duplicates the schema's default note, a small redundancy that keeps it from a 5.

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 two-parameter read-only tool with no output schema, the description covers the filtering rule and the units of a key returned field, which is enough to call it correctly. It says nothing about result ordering or volume, a minor gap given the absence of an output schema.

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 both parameters are already documented, including the includeFinished default. The description largely restates the includeFinished behavior and adds no new parameter-level detail; the minutes note refers to a returned value, not an input. Baseline 3 applies.

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 and resource ('List the tasks of a project') plus the domain purpose (man-hour tracking), which clearly separates it from list_projects, get_manhours, and the punch/stamp tools. Sibling routing is implied by the resource rather than explicitly stated, so it stops short of a 5.

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?

Gives a useful default-scope rule (finished tasks excluded unless includeFinished is true) but never says when to pick this over alternatives like get_today_status, get_manhours, or summarize_working_hours. Usage is implied by the resource rather than guided.

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?

Goes well beyond the destructiveHint annotation by disclosing that the timestamp is set at receipt time, that the record is immutable via the API and needs a web-UI correction request, and that conflicting punches are refused unless forced. These are exactly the consequences an agent needs before invoking a destructive write.

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 tight paragraph front-loads the verb and the type enum, then moves to the immutability warning and the force escape hatch. No sentence is filler and the highest-risk information is placed early.

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, output-schema-less write tool, it covers timing, immutability, conflict handling, and force semantics thoroughly. It leaves the telework parameter unmentioned and says nothing about what a successful call returns, both 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?

Schema coverage is 100%, so the enum, required flag, and force/telework meanings are already documented; the description repeats the type list and adds Japanese labels but no new syntax or format detail. It reinforces the force condition, but the baseline of 3 applies when the schema carries the parameter burden.

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 ('Record') and resource ('a punch') and enumerates every valid punch type, so the operation is unmistakable. It does not explicitly contrast itself with read-side siblings like get_stamps or get_today_status, which keeps it shy of a 5.

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?

Gives concrete decision rules: confirm the type with the user if unsure, and only pass force when the user insists after a conflict. It does not name alternative tools or say when to prefer a read tool first, so context is clear but exclusions are absent.

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 destructiveHint=true and idempotentHint=true, but the description adds the crucial nuance that only listed tasks are overwritten while other tasks on that day are kept — i.e. a partial merge, not a full-day replace. It also discloses the closed/fixed period lock, which is a real failure condition an agent must anticipate; what it omits is error/response behavior for locked days or invalid task-project pairings.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the mutation semantics, then the alternative tool, then ID discovery, then the lock constraint. Every sentence carries actionable information with no restatement of the name or title.

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 two-parameter mutation tool with no output schema, it covers write semantics, sibling routing, ID sourcing, and the locked-period precondition. Remaining gaps are edge-case behavior — what happens when a projectId/taskId pair mismatches, or the exact failure signal on a closed day.

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 50%: date and minutes are documented in the schema, but projectId and taskId are not. The description compensates by saying these IDs come from list_projects/get_my_projects and list_tasks, and by framing the payload as 'minutes per project task', which clarifies why both IDs are paired per entry.

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 pair (create or update) and resource (your own man-hours for one day), and further scopes the unit as 'minutes per project task.' It also names the sibling delete_manhours for the opposite operation, so an agent can distinguish it from get_manhours without opening a schema.

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 routing: removal goes to delete_manhours, ID lookup goes to list_projects/get_my_projects and list_tasks, and days that are closed (締め) or fixed (確定) cannot be changed. That is when-to-use, when-not-to-use, and prerequisites all in one place.

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 readOnly/openWorld annotations, it discloses that the overtime figure is an ESTIMATE (a correctness caveat the agent must relay), that results are scoped to the caller's own data, that output is broken down per month, and that the range is capped at 366 days. Auth requirements and empty-result behavior remain unstated.

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 dense sentence front-loads the purpose and enumerates outputs, followed by a short defaults/limits clause and the estimate disclaimer. The bilingual parenthetical glosses add length but serve the Japanese-domain audience; nothing is redundant with the schema.

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 only two optional parameters, no output schema, and annotations already covering the safety profile, the description is fully sufficient: it names every returned metric, the per-month structure, the default window, the maximum range, and the mandatory caveat about the overtime estimate.

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%, so the baseline is 3; the description earns above that by adding a constraint not in the schema — the 366-day maximum span — and by reiterating the default range meaningfully against the 'summarize over a period' purpose. It adds no format hints beyond what the YYYY-MM-DD patterns already say.

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 verb ('Summarize') on a specific resource ('your own working hours') and enumerates the exact aggregates returned: total actual working time, work days, holiday work days, overtime estimate, and per-month breakdown. The 'your own' scope implicitly separates it from team-level siblings like get_manhours or list_projects, but no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete operating context: defaults to the 1st of this month through today and caps the span at 366 days, plus an instruction to always disclose that overtime is an estimate. It never states when to prefer this over get_working_records or get_manhours (raw records vs aggregated summary), so no exclusion guidance is present.

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