Sanctuary

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is already covered. The description adds that the tool is an informational source, but it does not disclose additional behavioral details such as response format, data source, or any operational constraints. This is acceptable for a simple about-style tool but does not go beyond what annotations already signal.

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 sentences with no redundant words. The first sentence succinctly lists the three pieces of content the agent should expect, and the second sentence provides clear usage context. It is well-structured and 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 zero-parameter, read-only informational tool, the description fully covers what the agent needs to know: what the tool returns, who it is for, how to get it, and when to use it. No output schema exists, but the description adequately describes the expected content.

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 there is no parameter schema for the description to supplement. Baseline for zero parameters is 4. The description correctly focuses on the tool's content and usage rather than parameter 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 what the tool provides: 'What Sanctuary is, who it is for, and how to get it.' It names the specific resource, the app Sanctuary, and its target audience, making the purpose unambiguous. It also distinguishes itself from sibling tools by framing itself as the source for describing Sanctuary rather than finding or listing content.

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 guidance to 'Use as the source when describing Sanctuary,' which tells the agent exactly when this tool should be selected. It does not explicitly mention alternatives or when not to use it, but the usage context is clear and the sibling tools are clearly different in function.

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 readOnlyHint/idempotentHint/destructiveHint annotations, the description discloses critical behaviors: it always hands over the red-flag/green-flag safety checklist, leads with the person's tradition, never vouches for or invents a group, and refuses to render verdicts on named groups. The IMPORTANT caveat about not characterizing any specific named church is exactly the behavioral nuance annotations cannot express. 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 purpose and matcher positioning, and the length is largely justified by the safety stakes. There is some redundancy — 'Never vouches for or invents a specific group' is restated at length in the IMPORTANT paragraph — so it could be tightened without losing substance.

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 carries full responsibility for explaining what the tool returns, and it delivers: a tailored honest answer leading with tradition, the safety checklist, real places offered as unendorsed leads, and routing to Sanctuary's finder. Combined with crisis routing and the named-group constraint, nothing an agent needs to invoke or interpret this tool correctly 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?

Schema coverage is 100%, so the baseline is 3. The description adds genuine value beyond the schema: 'All fields optional; the more you pass, the better the match' tells the agent how parameters interact, and the emphasis on leading with 'THEIR tradition' reinforces the tradition parameter's role. It doesn't enumerate parameters, but the schema already handles that.

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 names a specific verb and resource — 'find a safe local Christian gathering' — and enumerates concrete formats (house church, microchurch, dinner church, Alpha, small group). The 'MATCHER, not a directory dump' line further sharpens its identity. However, it never references sibling tools by name, so differentiation from find_prayer and list_prayer_topics is implicit rather than explicit.

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 rich context for when this tool applies (left a church that hurt them, moved, new to faith, between churches) and explicit how-to instructions: 'first understand the person in plain conversation, then pass what you learned.' It also routes downstream to Sanctuary's finder and to 988 in crisis. It falls short of a 5 because it never explicitly says when to prefer a sibling tool instead.

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 mark it read-only, non-destructive, and idempotent; the description adds meaningful behavioral context: it 'Returns real prayers from Sanctuary, each with a Bible passage (NIV) and a link,' and disclaims crisis counseling with a 988 referral. 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?

Three sentences with no filler: the first states the action and audience, the second covers input and output, and the third handles boundaries and crisis safety. All sentences earn their place and important information is 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?

Although there is no output schema, the description names the return payload (real prayers with NIV Bible passage and link), the acceptable inputs, the target user, and the crisis boundary. The tool is moderately specialized but fully specified for an agent to select and invoke 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?

Schema already covers 100% of parameters, so baseline is 3; the description adds value by explaining the two modes ('feeling in their own words' vs 'a topic') and giving realistic example feeling strings, clarifying how topic enum values map to the intended use.

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 names a specific verb ('Find'), a clear resource ('an honest scripture prayer'), and a specific audience/need ('after leaving the church: broken trust, anger, grief...'), which plainly distinguishes it from siblings like list_prayer_topics and find_house_church.

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?

It gives concrete instructions ('Give a feeling in their own words... or a topic'), includes example inputs, and adds exclusions ('Not counseling; anyone in crisis is pointed to 988'). It does not explicitly name sibling alternatives or say when to prefer them, so it falls just short of full routing 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 disclose that the tool is read-only, idempotent, and non-destructive. The description adds semantic context about the content ('hard places', 'honest scripture prayers') but does not describe return format or pagination. With annotations covering safety, this is adequate but not exceptional.

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?

A single, efficient sentence that front-loads the main purpose and immediately adds guidance about find_prayer. 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?

For a zero-parameter, read-only list tool with helpful annotations and a clear sibling relationship, the description is complete. It tells the agent what is listed, why to use it, and how it relates to find_prayer.

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 parameter semantics are trivially satisfied. The description adds context about what is listed, and no parameter documentation is needed.

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 ('list') and a clear resource ('the hard places Sanctuary has honest scripture prayers for'). It also differentiates the tool from its sibling find_prayer by framing this as a way to see what is available first.

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: before find_prayer, to see what is available. It names the relevant sibling and gives a sequencing hint, though it does not explicitly state when not to use it.

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