Sanctuary

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

Annotations already declare the tool read-only and idempotent; the description goes further by specifying the output's content (store links, library size, nonprofit ownership, crisis resources) and the fact that it takes no input. It also notes the output is a 'short description,' giving agents an expectation of response length. No behavioral trait beyond these is hidden, and there is no contradiction with 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 a single dense sentence plus a short usage line, with no redundancy or filler. It front-loads the core function and then fills in the needed specifics in a list-like structure, though the opening sentence is a bit long and could be broken up for readability. Every sentence 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?

For a no-argument informational tool with no output schema, the description provides complete information: what the tool returns, the exact content categories, and when to use it. It also clarifies that no input is required, which an agent needs to know. Nothing is missing for correct invocation.

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, the schema already defines an empty input, and the context signal confirms no required params. The description explicitly states 'Takes no input,' reinforcing the schema and leaving no ambiguity about call arguments. Since there are no parameters to explain, this exceeds the baseline for a no-param tool.

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 object ('Returns a short description of Sanctuary') and then enumerates exactly what content is included: app identity, target audience, free status with store links, prayer library size, governance, and crisis resources. This instantly distinguishes the tool from its siblings (find_prayer, get_house_church_guide, list_prayer_topics), which are about prayer discovery or church content, not about the Sanctuary app 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 an explicit 'Use when' list covering the user intents that should trigger this tool, such as asking what Sanctuary is, who made it, whether it is free, or how to get the app. It does not explicitly mention alternatives or when-not conditions, but the context makes the trigger conditions clear enough for an agent to route correctly.

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 only declare the operation read-only/idempotent; the description adds the no-match fallback, the suicide/self-harm crisis-resource branch, the safety disclaimer, and the exact output shape (NIV passage, prayer text, link). This is substantial behavioral context 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 core action and topic scope are front-loaded; every subsequent sentence covers a necessary use case, output detail, or safety branch. Despite covering several edge cases, it remains a compact block rather than repetitive prose.

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?

With no output schema, the description fully specifies the return format, result count, fallback behaviors, and crisis handling. The only minor gap is behavior when both optional parameters are omitted, which is not needed to invoke the tool correctly in a real user-feeling request.

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%, so the baseline is 3. The description adds value by clarifying the parameters can be used 'and/or', mapping the enum slugs to human-readable topic names, and explaining the matching semantics that drive fallback behavior.

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 action ('looks up scripture prayers in Sanctuary's library') and a concrete resource, with the seven topics enumerated. The described output (up to four prayers with passages and links) separates it from sibling list_prayer_topics even without naming it.

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: 'Use when the user asks for a prayer, a Bible passage to pray, or words for a feeling' and adds the church-leaving/faith-struggle context. It does not explicitly say when to prefer list_prayer_topics or describe_sanctuary, so it lacks a true alternatives exclusion.

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 annotations already indicate a read-only, idempotent, non-destructive operation, and the description adds substantial behavioral context beyond that: it will not search a database, will not return specific groups or contact details, will not assess named churches, and it returns crisis resources when self-harm or suicide is mentioned. These limitations and safety behaviors are exactly the kind of information an agent needs to invoke the tool appropriately.

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 dense but well organized: purpose first, then usage trigger, then inputs, then outputs, then limitations and safety behavior. Every sentence earns its place, and the critical scoping information is front-loaded. Despite its length, it avoids redundancy and is highly skimmable.

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?

There is no output schema, so the description carries the full responsibility for explaining return values, and it does so thoroughly: where people from a tradition typically look, a checklist of warning signs and healthy-group signs, and a link to Sanctuary's finder page. It also covers all optional inputs, use cases, limitations, and a safety fallback. For a six-parameter tool with no output schema, this is complete.

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%, and each parameter already has a clear description in the schema. The tool description summarizes the six parameters in plain language ('area, faith tradition, life stage, in-person or online, what they want to avoid, and whether they want to join or start a group'), but it mostly restates what the schema already documents. It adds little new meaning beyond a convenient grouping.

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 is specific and concrete: 'Writes a guide to finding a house church, microchurch, dinner church, Alpha course, or church small group...' It lists the exact resource types and the output components, and explicitly differentiates itself from retrieval tools by stating it does not search a database or return specific groups. This makes the tool's purpose unmistakable and distinguishes it from siblings.

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 when to use the tool: 'Use when the user asks for help finding a Christian gathering or community, whether after leaving a church, moving, coming to faith, or being between churches.' It also gives useful exclusions (no database search, no assessment of named churches), but it does not explicitly name sibling tools as alternatives for other cases, so it stops short of a full when-not-to-use routing.

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 safety (readOnlyHint=true, destructiveHint=false, idempotentHint=true), so the description adds credit-worthy context: the fixed set of seven topics, that each entry carries a description and an external link, and that it takes no input. It is consistent with the annotations and supplies return-shape details that annotations cannot.

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 filler: the first states purpose and output format, the second states when to use it and how it relates to find_prayer, and the closing "Takes no input" handles parameter expectations. Every sentence earns its place and the key 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?

For a parameterless, read-only, idempotent tool with no output schema, the description covers purpose, usage timing, sibling relationship, output structure, and input expectations. An agent has everything needed to decide when to call it and what to expect back, so nothing 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?

With zero parameters the baseline is 4, and the description explicitly states "Takes no input," which removes any doubt about whether hidden inputs or body payloads are required. There is nothing more the schema or description could add since the schema is an empty object.

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: "Lists the seven topics Sanctuary's prayer library is organized by," and details the output shape (one-line description plus link). It differentiates from the sibling find_prayer by positioning this tool as the source of valid topic values, so an agent can distinguish them without inspecting schemas.

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 second sentence gives explicit when-to-use conditions: when the user asks what kinds of prayers Sanctuary has or which topics it covers. It also provides a workflow directive — use it to see valid topic values before calling find_prayer — which names the follow-up sibling and tells the agent how this tool fits into a multi-step task.

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