D8ly Read

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description's job is lighter. It adds valuable context by stating it applies True Solar Time correction and requires the subject's permission, which goes beyond the annotation-provided profile.

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 well-structured: first sentence states the primary use case, second sentence lists exclusions (plus a permission note). It is somewhat long due to bilingual repetition, but every clause contributes directly to correct invocation, making it appropriately concise.

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

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

Given that an output schema exists and parameter descriptions cover the inputs, the description sufficiently covers usage conditions, required data, and behavioral notes. It lacks explicit mention of output format, but that is the output schema's responsibility. It is complete enough for an agent to call 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?

With 100% schema coverage, the baseline is 3. The description adds semantic nuance by referring to the 'historical UTC offset,' clarifying that the timezone parameter is for the birth date, not the current one. This is a meaningful addition beyond the schema's simple offset description.

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-resource pairing: it calculates a Four Pillars birth chart given explicit birth data. It distinguishes itself by explicitly excluding inference of missing details or personalized guidance, which differentiates it from sibling tools like get_daily_bazi_guidance.

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 provides explicit when-to-use ('when the user wants a Four Pillars birth chart and has explicitly supplied...') and when-not-to-use ('Do not use this to infer missing birth details, daylight-saving rules, or personalized guidance') conditions, effectively routing the agent to the correct tool. The additional consent requirement adds a practical usage constraint.

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 the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar for the description is lower. The description adds valuable behavior beyond annotations: 'No generative AI is used' discloses the computation method, and the scope boundary (no personal birth data) clarifies what kind of calculations are involved. No contradiction with 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 English portion is three tight sentences: trigger condition, return fields, exclusions, plus a one-sentence behavioral note. Information is front-loaded with the usage condition before the payload list. The bilingual duplication roughly doubles length, but it's purposeful for a Chinese/English almanac tool serving both locales, so it 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?

Complete for a read-only lookup tool: an output schema exists so return format needs no prose explanation, both parameters are fully covered by the schema, annotations carry the safety profile, and the description covers when to use, when not to use, and what data scope applies. With only 2 simple parameters and siblings named, nothing an agent needs 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% — both date (with pattern and format) and locale (with enum and default) are fully documented in structured form. The description adds no parameter detail beyond restating that the tool is for a 'specific calendar date,' which maps to the date param. Per rubric, baseline 3 is correct when schema does the heavy lifting.

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: returns Chinese almanac data for a calendar date. Clearly names the return payload (day pillar, lunar date, activities, directions, zodiac clash) and explicitly differentiates from siblings by stating it does NOT do Bazi charts or daily Bazi guidance. A tool name alone (get_daily_almanac) plus this description tells the agent exactly what this is and is not.

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 an explicit trigger condition ('when the user asks for Chinese almanac information for a specific calendar date without personal birth data'), and an explicit exclusion ('Do not use this for a personalized Bazi chart or daily Bazi guidance'), implicitly routing the agent to the named siblings. The agent needs no inference to decide tool selection.

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, covering safety and side-effect behavior. The description adds valuable context beyond these: 'No generative AI is used' and 'Use only with the subject’s permission', which inform the agent of privacy and non-generative nature. This enriches the description without contradicting 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 front-loaded with the primary usage condition ('Use this when...') and states exclusions and key behavioral notes in subsequent sentences. It is bilingual, repeating content in Chinese, which doubles length but is appropriate for a localized tool. Each English sentence earns its place, though the repetition slightly reduces conciseness.

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

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

Given the output schema, 100% parameter coverage, and annotations, the description adequately covers when to use, exclusions, permissions, and the output nature. It doesn't mention error handling or edge cases, but these are less critical given the structured schema and clear prerequisites. The description is sufficient for an agent to call 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 100%, so every parameter (birth_date, birth_time, latitude, longitude, timezone, reading_date, locale) already has detailed documentation. The description's mention of 'complete birth inputs' reinforces the requirement but adds no additional semantic meaning beyond the schema. Baseline 3 is appropriate since the schema carries the full 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?

The description clearly states the tool's purpose: providing personalized daily Bazi guidance for a specific reading date when complete birth inputs are supplied. It explicitly contrasts with a 'date-only almanac request', distinguishing it from the sibling get_daily_almanac. The verb 'returns' and resource 'chart and daily guidance' make the function unambiguous.

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 explicitly states when to use the tool ('when the user wants personalized daily Bazi interactions... and has supplied the complete birth inputs') and when not to use it ('Do not use this for a date-only almanac request or when any birth input is missing'). It also adds a permission requirement, giving clear conditions and exclusions without ambiguity.

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