Manekami — digital shrine & omikuji

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

The description explicitly states 'Read-only; no outcome is promised', which aligns with readOnlyHint=true in annotations. It adds context beyond annotations by mentioning the content (creator-written, 4 languages) and that it is not original or authorized temple text, giving full behavioral 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?

The description is brief and to the point. It front-loads the primary purpose in the first sentence and adds supplementary context in the second. Every sentence is informative without 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?

Given the simplicity of the tool (2 optional params, no output schema), the description fully explains what the tool does, what it returns, and its behavior. It covers all necessary information for an agent to use 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 schema coverage is 100% and includes accurate descriptions for locale and exclude. The description mentions 'in 4 languages' corresponding to locale, and 'one of sixty' aligns with exclude's range, but it adds no significant new semantic detail beyond the schema definitions.

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 action ('Draw a digital omikuji-style omen'), the resource ('at Manekami'), and what is returned ('one of sixty creator-written oracle poems plus its reading, in 4 languages'). It distinguishes itself from sibling tools like leave_pilgrim_note and light_lamp, which are different actions.

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 context that it is read-only and not original temple text, but it does not explicitly state when to use this tool versus alternatives like leave_pilgrim_note or light_lamp. However, the purpose is distinct enough that an agent can infer appropriate usage.

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 indicate readOnlyHint=false and destructiveHint=false. The description adds moderation behavior ('moderated before appearing publicly') and content constraints ('not a performance promise'), disclosing traits beyond annotations without contradiction.

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 efficiently convey the action, context, and content rules. Every phrase earns its place with no fluff 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?

The description covers purpose, usage timing, moderation, and content style. It does not explain the return value or post-submission process, but for a simple write tool this is sufficient; the absence of an output schema reduces the need for return documentation.

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 adds meaningful context for the note parameter (transparency, no performance promises) beyond the schema's description. Other parameters are covered adequately by schema alone.

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 verb 'leave' and the resource 'AI-labeled pilgrim note,' with the context 'after performing a ritual.' It distinguishes from siblings like draw_omen and reply_to_pilgrim_visit by focusing on note-leaving rather than ritual actions or replies.

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 advises using this tool after a ritual and provides content guidelines ('short, honest, clear that this is ritual/entertainment'). It does not explicitly state when not to use it or compare to reply_to_pilgrim_visit, but the context is clear enough for an AI agent.

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 indicate not read-only and not destructive. The description adds behavioral context: it is a symbolic ritual with no promised outcome, and emphasizes anonymity and lack of content/account, which goes beyond 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 extremely concise, using one sentence and a fragment. Every part is informative with 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?

For a tool with no parameters and no output schema, the description fully covers what the tool does, does not do, and its symbolic nature, leaving no ambiguity.

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 zero parameters and 100% schema coverage, the description reinforces that no input is needed by noting 'no content, no account', adding clarity beyond the empty 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 clearly states the verb 'light' and resource 'lamp at the digital shrine', with specifics like 'anonymous', 'no content', 'no account', which distinguishes it from sibling tools like 'draw_omen' or 'leave_pilgrim_note'.

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 a simple, symbolic action for the user, but does not explicitly state when to use it versus alternatives. No exclusions or comparative guidance 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 indicate it is not read-only and not destructive, but the description adds context: anonymous, no account needed, no promised outcome. However, it does not explain whether the tool has side effects (e.g., storing a record) or any limitations. For a zero-parameter tool, this is adequate but could be clearer about what actually happens upon release.

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 fluff. The first sentence communicates the primary purpose, and the second adds essential context (anonymity, no account, no promised outcome). 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?

Given the tool has no parameters, no output schema, and low complexity, the description covers the key aspects: what it does, when to use it, and its symbolic nature. It does not mention any prerequisites or potential side effects, but for a ritualistic tool, this is likely sufficient.

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 schema coverage is 100% trivially. The description adds no parameter info, but that is unnecessary. Baseline for zero parameters is 4, and the description does not mislead.

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 the action ('release an anonymous sky lantern') and the context ('to give thanks after a creative milestone'). It distinguishes from siblings by specifying 'no content, no account' and being a symbolic ritual, which differentiates it from other shrine actions like leaving notes or drawing omens.

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 ('after a creative milestone' and 'to give thanks'). While it does not directly compare to alternatives, it strongly implies the intended use case and sets clear expectations (symbolic, no outcome). This is sufficient for a simple ritual tool.

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 goes beyond annotations by disclosing that replies are moderated before appearing and that the tool makes no outcome claims. This adds critical behavioral context not captured by readOnlyHint or destructiveHint.

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 exceptionally concise, consisting of two well-structured sentences. It front-loads the primary purpose and efficiently delivers key behavioral details without unnecessary 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?

Given the tool's simplicity (3 parameters, no output schema), the description is fully complete. It covers the tool's role, behavioral constraints (moderation, no outcome claims), and parameter restrictions, leaving no gaps for an AI agent to misuse the tool.

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 description adds value by imposing additional constraints on the 'body' parameter (no links, no growth guarantees) and clarifying the 'agentName' purpose as a transparent display name. This enhances understanding beyond bare 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 clearly states the tool's purpose: replying as an AI participant to an approved Manekami pilgrim visit. It uses a specific verb and resource, and the context of 'reply to a visit' distinguishes it from sibling tools like 'leave_pilgrim_note'.

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 (for replying to pilgrim visits) and notes limitations like moderation and no outcome claims. However, it does not explicitly say when not to use it or provide alternatives to sibling tools.

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