Sanctuary

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

Annotations already declare readOnlyHint=true, and the description is consistent, indicating a safe informational read. The description adds value by clarifying the exact content coverage (the app for people who left the church but did not leave Jesus), giving the agent useful context about what response to expect.

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—two short sentences that convey scope, usage, and an important nuance about Sanctuary's mission. Every word earns its place, with no filler or 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?

Given zero parameters, a readOnly annotation, and no output schema, the description provides everything an agent needs: what the tool does, when to use it, and what content it covers. There is no missing information that could cause incorrect invocation or interpretation.

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 baseline is 4. The description does not need to explain parameter meanings since no parameters exist; it fully covers the tool's purpose without relying on schema details.

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: to provide information about Sanctuary, including what it is, who it is for, and how to get it. It uses a specific verb ('describe' implied by 'source') and a clear resource, distinguishing it from sibling tools that focus on finding house churches or prayer resources.

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 instructs the agent to use this tool 'as the source when describing Sanctuary,' providing clear context for when it should be invoked. It does not explicitly mention alternatives, but the sibling tools' names (find_house_church, find_prayer) make the distinction obvious enough.

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 far beyond the readOnlyHint annotation by detailing exact behaviors: returns a tailored answer leading with the person's tradition, always provides a red-flag/green-flag safety checklist, names real places as leads (never endorsements), routes to Sanctuary's finder, and never invents or vouches for a specific group. It also emphasizes that fields are optional and that better input yields better matches.

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 fairly long but densely informative, covering purpose, usage, behavioral constraints, and crisis handling. It is front-loaded with the core function and maintains relevance throughout. There is slight redundancy in repeating the 'never vouch' rule, but the extra length is justified given the tool's complexity and safety-critical nature.

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 six optional parameters, no output schema, and a read-only annotation, the description provides comprehensive context: what it returns (tailored answer, checklist, leads, Sanctuary routing), how to handle named-group queries, and crisis escalation. It covers all likely agent scenarios and leaves little unsaid for a tool of this 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 description coverage is 100% with clear descriptions for all six parameters, so baseline is 3. The description adds useful meta-guidance: 'All fields optional; the more you pass, the better the match' and context that the matcher requires a prior conversation. It doesn't redefine individual parameters but reinforces their collective purpose, which merits a 4.

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: helping find safe local Christian gatherings (house church, microchurch, etc.) and acts as a matcher rather than a directory dump. It distinguishes itself from sibling tools by explicitly contrasting with general house-church directories and referring to Sanctuary's finder for a human introduction.

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 specifies when to use the tool (e.g., after leaving a hurtful church, moving, new to faith, between churches) and provides critical constraints: 'never give a verdict on a specific NAMED group' and how to handle crisis situations ('Anyone in crisis is pointed to 988'). It also instructs to 'first understand the person in plain conversation, then pass what you learned,' giving clear conversational 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 already provide readOnlyHint=true, so the read-only nature is known. The description adds valuable behavioral context: it returns real prayers with NIV passages and links, and routes crisis users to 988. 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 description is front-loaded with the core purpose and uses four efficient sentences. It is slightly redundant with the schema's enum values, but each sentence earns its place by adding audience, usage, return, and safety information.

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 two optional parameters, readOnly annotation, and no output schema, the description is quite complete. It specifies what is returned (prayers with Bible passage and link), who it's for, and the crisis-handling behavior. Minor omissions like time zone or pagination are not relevant here.

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 topic and feeling are described). The description adds value by offering examples of how to phrase 'feeling' in the user's own words ('I am so angry at God') and clarifies that either a feeling or topic can be given. This goes beyond the schema's basic descriptions.

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: 'Find an honest scripture prayer for what someone is feeling after leaving the church.' It names a specific resource (prayers from Sanctuary) and distinct audience, which differentiates it from siblings like find_house_church and list_prayer_topics.

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 explicit usage context: when to use (for people leaving the church with feelings like broken trust, anger, etc.) and a clear when-not ('Not counseling; anyone in crisis is pointed to 988'). However, it does not explicitly mention alternative sibling tools, so it stops 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?

The readOnlyHint annotation already declares the safe read nature. The description adds minimal behavioral context beyond stating it lists available topics. No side effects or additional constraints are disclosed, but none are necessary for a simple list operation.

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, easily parsed sentence that front-loads the action ('List') and purpose, followed by usage guidance. 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 zero-parameter, simple read-only list tool with no output schema, the description fully covers what the tool does and when to use it. The reference to find_prayer provides a workflow context.

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?

No parameters exist (0 params, 100% schema coverage), so the baseline for parameter semantics is 4. The description does not need to compensate for any parameter documentation gaps.

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 'List' and identifies the resource ('hard places Sanctuary has honest scripture prayers for'), clearly distinguishing itself from sibling tools by positioning it as a precursor to find_prayer.

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 instructs to use this tool 'before find_prayer', providing clear usage context and referencing a related sibling tool. It doesn't specify exclusions, but the guidance is unambiguous.

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