Love Oracle — Tarot

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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds that calling with no slug returns a list of questions and that output is markdown, which is useful. But it doesn't disclose behavior beyond these — no info on pagination, answer length, or what happens with unsupported language values.

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, front-loaded with the core purpose, includes the key usage note about omitting slug, and states the return format. Zero 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 read-only lookup tool with clear purposes, a 2-param schema, and 100% schema coverage, the description covers the essentials well. It would benefit from a small note distinguishing this from sibling tools (e.g., single card meaning vs. question-answer), but overall it's complete for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are well-described in the schema itself. The description adds value by explaining the slug-omission behavior (list all questions), which goes beyond the schema. Language parameter is fully documented with enum values in the schema, so the description doesn't need to repeat it.

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

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

Description clearly states it returns the long-form answer to common love-tarot questions and which cards speak to them. It lists concrete examples ("will he come back", "does he miss me") and specifies the output format (markdown). Distinguishes itself from siblings which are about individual card meanings and card search.

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?

Description explicitly says calling with no slug lists available questions, which is clear usage context. However, it doesn't explicitly state when to prefer this over sibling tools like get_tarot_card_love_meaning or search_tarot_cards, leaving some ambiguity about differentiation.

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 readOnlyHint=true annotation already declares this a safe read operation, so the bar is lower. The description usefully indicates the output is markdown and enumerates the exact content dimensions returned, which adds behavioral context beyond the annotation. It doesn't describe pagination or size limits, but for a single-card lookup these aren't material.

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 dense sentences with zero waste. The first sentence enumerates all content dimensions, the second states the output format (markdown). Every element earns its place and important facts are front-loaded.

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?

This is a straightforward read-only lookup tool with 100% schema coverage, readOnlyHint annotation, and no output schema needed. The description fully enumerates what content the response covers (upright, reversed, feelings, ex, yes/no, element) plus output format. Nothing essential is missing for an agent to use this 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 coverage is 100%, so both parameters (slug and language) are fully documented in the schema. The description adds value by stating slug should always be the English slug, which supplements the schema. Beyond that, schema already handles the heavy lifting, so baseline 3 is appropriate.

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: what a single tarot card means for love and relationships. It enumerates the specific dimensions covered (upright, reversed, feelings, ex context, yes/no leaning, element), clearly distinguishing this from sibling tools like get_love_question_answer and search_tarot_cards. The scope is precise and leaves no ambiguity about what it returns.

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 looking up love-related meanings of a specific card, which differs from the sibling tools (get_love_question_answer for question answering, search_tarot_cards for searching). However, it does not explicitly state when to use this tool vs the alternatives, nor note any prerequisites or 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 declare readOnlyHint=true and openWorldHint=false, which covers the safety profile. The description adds that it returns 'slugs the other tools take,' which is useful behavioral context about its output purpose. However, it doesn't disclose the return format, result count limits, or behavior on no-match queries. With annotations covering the read-only safety, 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?

Two concise sentences with zero filler. The first states the core action and output, the second gives crisp usage direction. Well front-loaded and to the 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?

For a search/lookup tool with full schema parameter coverage, read-only annotations, and only 2 params, the description is complete. It explains what it does, what it returns (slugs for other tools), and when to use it. The absence of an output schema is compensated by the clear statement that it returns matching cards with slugs, which is sufficient for an agent to proceed.

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 parameters (query, language) have descriptions in the schema itself. The description adds 'part of a card name in any supported language' context for the query parameter and explains that the search is partial-match ('part of a card name'), which adds modest value beyond the schema. Baseline 3 is correct here as the description offers some extra nuance but the schema already 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?

The description states a specific verb+resource ('Search the 78-card Rider–Waite–Smith deck by name') and clearly distinguishes its purpose from the sibling tools (get_love_question_answer, get_tarot_card_love_meaning) by noting it 'return[s] matching cards with the slugs the other tools take.' This positions it as the lookup/bridge tool that precedes others.

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 when-to-use guidance: 'Use this first when you only have a card name.' This clearly indicates it's the entry-point tool when only a name is known, contrasting with the sibling tools which consume the slugs it produces. This is strong, actionable usage direction.

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