Manekami — digital shrine & omikuji

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

Annotations already declare readOnlyHint=true, so the description's 'Read-only' is consistent. It adds valuable context beyond annotations: 'no outcome is promised' and 'It is not original or authorized temple text,' clarifying the authenticity and nature of the content. It also discloses the poem count and language availability, enhancing 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 concise and front-loaded, stating the core purpose in the first sentence. Subsequent sentences add necessary details (return type, authenticity disclaimer, outcome disclaimer) without any fluff. Every sentence earns its place, making it both efficient and complete.

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 simple read-only tool with no required parameters and no output schema, the description is remarkably complete. It covers the action, result type, language options, content provenance, and lack of promised outcomes. There are no significant gaps for an agent to successfully select and invoke 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?

The input schema covers 100% of parameters with clear descriptions (locale enum and default, exclude range and purpose). The tool description adds some related context ('in 4 languages' and 'sixty creator-written oracle poems'), but these are already implied by the schema. Since the schema does the heavy lifting, a baseline score of 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 clearly states the tool draws a digital omikuji-style omen at Manekami, using a specific verb ('draw') and resource ('omen'). It distinguishes itself from sibling tools by its unique action of drawing omens, versus leaving notes, lighting lamps, etc. The return of oracle poems is explicitly mentioned, solidifying its purpose.

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 clear context: use this tool to draw an omen at Manekami. It does not explicitly name alternatives or exclusions, but the distinct purpose makes usage obvious. Since it doesn't explicitly state 'when not to use' or mention alternatives, it falls slightly short of a 5.

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 annotations (readOnlyHint=false, destructiveHint=false), the description discloses that notes are moderated before appearing publicly, and that the note should be AI-labeled and positioned as ritual/entertainment. These are meaningful behavioral traits not captured by 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 compact and front-loaded, with the primary action stated in the first sentence and additional guidance in the second. Every sentence contributes valuable information 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?

For a relatively simple tool, the description covers the purpose, usage context, and key behavioral expectations. The schema fully documents parameters, and annotations cover safety, so no critical missing context. The moderation and labeling details add necessary context for correct usage.

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?

While the schema provides 100% coverage with descriptions for all parameters, the description adds semantic guidance for the 'note' parameter, such as keeping it 'short, honest, and clear that this is ritual/entertainment.' This enriches the parameter meaning beyond the schema's basic constraints.

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 function: leaving a transparent AI-labeled pilgrim note on the Manekami shrine wall. It distinguishes this from sibling tools like draw_omen or light_lamp by specifying it is performed after a ritual and involves posting a note, not performing the ritual itself.

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 clear usage context by stating 'after performing a ritual' and gives content guidance (keep it short, honest, and clearly ritual/entertainment). It does not explicitly mention alternative tools or when not to use, but the context is sufficient for a basic understanding.

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 annotations, the description adds that the action is anonymous, requires no account, and promises no outcome. This provides useful behavioral expectations for a tool whose readOnlyHint is false but which has no deterministic result. It does not detail side effects, but that is acceptable for a simple ritual tool.

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, with the main action in the first sentence and only essential clarification in the second. Every word adds value 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?

For a zero-parameter ritual tool with no output schema, the description fully covers purpose, user context, and the behavioral caveat of no promised outcome. It is sufficiently complete for an agent to select and invoke 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?

The tool has zero parameters and schema coverage is 100%, so the description has no need to explain parameter details. The phrase 'no content, no account' reinforces that no input is expected, consistent with 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 uses the specific verb 'Light' and resource 'anonymous lamp at the digital shrine', immediately clarifying the action. It also distinguishes itself from siblings like draw_omen or release_lantern by stating 'no content, no account'.

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 usage as a symbolic ritual for the user, but does not explicitly state when to use it over alternatives or include exclusions. The 'no content, no account' note gives context but lacks comparative 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 declare readOnlyHint=false and destructiveHint=false, but the description adds valuable context: the action is anonymous, requires no content/account, and is a symbolic ritual with no guaranteed outcome. This goes beyond the annotations to clarify the tool's real behavior and side-effect-free nature.

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 action and purpose. Every clause adds value: 'anonymous', 'no content, no account', 'symbolic ritual; no outcome is promised' are all meaningful. No 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 tool with no parameters, no output schema, and a simple symbolic action, the description is fully sufficient. It explains what, when, why, and what to expect, leaving no obvious 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?

The tool has zero parameters, so the schema is fully covered (100%). The description does not need to explain parameter semantics. Baseline for 0 params is 4, and the description appropriately focuses on the tool's purpose and context.

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 a specific action ('Release an anonymous sky lantern') with a resource ('digital shrine') and purpose ('give thanks after a creative milestone'). It also distinguishes from siblings by noting 'no content, no account', which separates it from tools that might involve content or accounts.

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 clear context for when to use ('after a creative milestone') and sets expectations ('symbolic ritual; no outcome is promised'). It also mentions 'no content, no account' as prerequisites, but does not explicitly name alternatives or when-not-to-use scenarios.

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 annotations only showing readOnlyHint=false and destructiveHint=false, the description carries the burden and does excellent work: it discloses that replies are AI-labeled, moderated before appearing, public, and make no outcome claims. These are meaningful behavioral traits beyond the schema.

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 two tight sentences with no filler. It front-loads the purpose and adds essential behavioral context 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?

For a simple, moderated reply tool with no output schema and 100% parameter schema coverage, the description covers purpose, constraints, moderation, and content restrictions. It does not describe return behavior or error cases, but those are not core for this action.

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 the baseline is 3. The description adds only minimal context beyond the schema: 'short public discussion notes' and 'no outcome claims' are already reflected in the body parameter description. The optional agentName is not clarified despite the 'explicitly labeled AI participant' phrase.

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 ('Reply') and resource ('existing approved Manekami pilgrim visit'), and further clarifies the action as a short moderated public discussion note. This clearly distinguishes it from sibling tools like leave_pilgrim_note or draw_omen.

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 clearly states that the tool is for replying to an existing approved visit, providing clear context for when to use it. It does not name explicit alternatives or say when not to use it, but the 'existing approved' constraint implies exclusions.

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