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

No annotations are supplied, so the description carries the full burden and does a solid job: it discloses the return shape (both sides with timezone, UTC offset, weekday, plus the time difference) and the DST edge-case behavior (a note when a time is skipped or repeated). The remaining gap is minor for a pure computation tool — no side effects, no auth or rate-limit concerns are mentioned, though none plausibly apply.

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 the action and the return contract, then the DST caveat, then the input grammar — a sensible order with no filler. The long format enumeration is dense but every item removes a real ambiguity about what will parse.

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?

An output schema exists, yet the description still summarizes the return contract and the one non-obvious behavioral wrinkle (DST skip/repeat notes), and it fully covers the two required inputs. Nothing an agent needs in order to call this correctly 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?

Schema coverage is 100%, so the baseline is 3, but the description earns an upgrade by enumerating concrete accepted forms for 'time' — ISO date, space-separated datetime, offset-bearing ISO, slash-separated, Japanese era names such as '令和6年12月10日' and 'R6.12.10', and time-only treated as today — which the schema's one-line example does not convey. It also reinforces that an offset written in the input overrides source_timezone. The 'format' parameter is left to its schema description by reference to get_datetime, so this is not a 5.

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 ('Convert a time or date-time from one timezone to another') and immediately scopes what the result contains. Against siblings get_datetime, shift_datetime and get_datetime_info, the timezone-conversion framing is distinct enough that an agent can route correctly 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?

Usage is implied by the purpose: convert when you have a time in one zone and need it in another. There is no explicit when-to-use versus shift_datetime or get_datetime, and no stated exclusions or prerequisites. The accepted-input-forms list indirectly tells the agent this tool is the right one for parsing loose date strings, but that is inference rather than guidance.

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

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the default timezone source (the server machine's local zone), the IANA override, the full set of supported directives, and a concrete boundary condition (Japanese era supported from 1873-01-01). It says nothing about side effects, cost, or rate limits, though for a pure clock read those gaps are minor.

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?

Purpose, timezone behavior, then format reference is a sensible front-loaded order. The 25-item format table is long but earns its place because the schema declares no enum, so this is the only place the valid names exist; a slightly tighter grouping of the filename_* and wareki variants would trim it further.

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?

An output schema exists, so return-value explanation is correctly omitted, and both parameters are fully covered with defaults and fallback behavior. The one missing piece relative to a four-tool family is routing guidance distinguishing this from the conversion, shifting, and info siblings.

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 already 100%, yet the description goes well beyond it by enumerating every accepted format name with a rendered example and by documenting custom strftime patterns and the Japanese %J directives that the schema only alludes to. That is exactly the meaning an agent needs to construct a valid 'format' value.

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 first sentence gives a specific verb and resource ('Get the current date and time') plus the format scoping. It never mentions the siblings convert_time, shift_datetime, or get_datetime_info, so an agent cannot tell from the description alone that this tool only reads the current instant rather than converting or offsetting one.

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 only implied: 'current' signals a read of now, and the timezone sentence hints at localization. There is no explicit statement about when to prefer get_datetime_info over this tool, or that this tool is inappropriate for arithmetic on existing timestamps (which the sibling tools cover).

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

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

With no annotations, the description carries the full burden, and it does: it discloses that everything defaults to now, that a reference date enables a signed day/second delta, and that multiple timezone representations are produced for the same instant. It doesn't discuss error behavior when an input form is unparseable, but the tool is a transparent read-only computation.

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 purpose, then defaults, then result fields, then accepted formats – a sensible order with no filler sentences. The long field enumeration is dense but each item is informational rather than padding.

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?

An output schema exists, yet the description still enumerates key fields, which is mildly redundant but helps the agent decide to call it. Inputs, defaults, comparison semantics, and accepted formats are all present; only sibling routing and parse-failure behavior are 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?

Schema coverage is 100%, so baseline would be 3, but the description adds real value the schema lacks: a concrete list of accepted datetime input formats (ISO, slash-separated, Japanese kanji form, era notations like '令和6年12月10日' and 'R6.12.10', and time-only meaning today). That format guidance is the main practical risk of mis-calling the tool and it is covered.

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 opens with a specific verb and resource ('Get details of a date-time') and then enumerates the exact fields returned (ISO, timezone, wareki, ISO week, quarter, diff from reference), making the scope unambiguous. It doesn't explicitly name the siblings get_datetime/convert_time/shift_datetime, so differentiation is implied by the inspection framing rather than stated.

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 states the useful defaults (omit for now, reference defaults to now) and gives a concrete use case ('how many days until a date'), which implies when to call it. It never says when to prefer it over convert_time or shift_datetime, so the agent must infer the boundary from sibling names alone.

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

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

With no annotations at all, the description carries the full burden and does substantial work: it discloses the calendar-vs-elapsed distinction between years/months/weeks/days and hours/minutes/seconds, and the month-end clamping rule with a concrete example (2024-01-31 + 1 month = 2024-02-29). This is non-obvious behavior an agent could not infer from the schema. It does not say what happens on unparseable input or how errors surface, which keeps it below a 5.

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 core action and default are front-loaded in the first sentence, followed by semantics and then a format list. The long enumeration of accepted forms is dense but each example adds real parsing knowledge rather than restating the schema. It is a single unbroken paragraph, which slightly hurts scannability but not substance.

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 10-parameter, all-optional tool with no annotations, the description covers the defaults, the unit semantics, the month-end edge case, and the full range of accepted input formats. Return values are handled by the existing output schema, so leaving them out is correct. Nothing an agent needs in order to construct a valid call 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?

Schema description coverage is only 30%, so the description must compensate, and it does: the accepted base formats are enumerated in detail (ISO, slash form, Japanese, era notation, time-only) and the six unit parameters are given real meaning via the calendar/elapsed distinction and negative-value rule. The 'format' parameter is left to the schema's reference to get_datetime, and timezone is not discussed in the description, so the compensation is strong but incomplete.

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

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

The description opens with a specific verb+resource: 'Add or subtract an amount of time to a date-time (default: now)'. An agent can immediately distinguish this arithmetic tool from get_datetime (read current) and convert_time (timezone conversion) without opening the schema. It stops short of naming those siblings explicitly, so it is clear but not fully differentiated.

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 useful calling guidance: omit 'base' to start from now, and use negative numbers to shift into the past. However, there is no statement of when to prefer this over convert_time or get_datetime, and no exclusions or error conditions. Usage is implied by the purpose rather than stated against alternatives.

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