GospelChannel Church Finder

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

Annotations declare readOnlyHint=true and destructiveHint=false, so the description does not need to repeat those. The description adds the behavioral detail of ranking by directory quality, which hints at an ordering behavior not present in the schema. However, it does not disclose how results are returned (e.g., list size, pagination) or what the output format is. The output schema exists, so return values are covered elsewhere. The added ranking behavior is useful context beyond annotations, warranting a mid-range score.

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 sentence that front-loads the primary action and resource ('Find Christian worship churches in a named city'), then states the ranking criterion and the filter options. Every word earns its place; there is no redundancy or filler. It is concise yet informative, making it easy for an agent to parse quickly.

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, the description covers the essential context: what it does (find churches), the ranking basis (directory quality), and the available filters. The output schema exists, so return structure is already defined. The only minor gap is that it doesn't specify the default limit or maximum, but these are documented in the parameter schema. Overall, the description is complete enough for an agent to 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 description coverage is 100%, and the description explicitly mentions the filter parameters (worship style, denomination, language) as well as the main required city parameter. The description does not add extra meaning beyond what the schema provides; it just summarizes the filters. Since the schema already fully documents each parameter with descriptions, the baseline is 3, and the description adds some clarity by listing them together but no new semantic 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: finding Christian worship churches in a named city, with ranking by directory quality and optional filters. It specifies the verb 'find' and the resource 'churches in a city', distinguishing it from siblings like find_churches_near (which likely searches by proximity) and get_church (singular). The scope is explicit and unambiguous.

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 context: use when you need churches in a specific city, with filters for worship style, denomination, or language. It does not explicitly mention when not to use it or alternatives (e.g., find_churches_near for location-based queries), but the context signals list sibling tool names, and the description's clear city-based scope provides enough guidance for an agent to select this tool appropriately.

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 state readOnlyHint=true and destructiveHint=false, so the read-only nature is covered. The description adds valuable behavioral detail: it relies solely on coarse location metadata and never on raw user-provided location fields, and results are distance-ranked. This goes beyond annotations by explaining the source and sorting logic.

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 clear, dense sentences with no filler. The primary purpose comes first, followed by the key location-source caveat, then filter options. Every sentence earns its place and no redundant wording appears.

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 read-only tool with five optional params and an output schema (not shown but present), the description covers the essential special aspect (how location is obtained). It omits minor details like return format or no-result behavior, but given the output schema exists and the operation is non-destructive, the context is largely 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?

Schema coverage is 100% — every parameter has a description in the input schema. The description only restates that filters are available ('worship style, denomination, or language'), which adds no new semantics beyond the schema. Baseline 3 is appropriate because the schema carries the param meaning.

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: 'Find Christian worship churches near the user, ranked by distance.' It further clarifies the unique input mechanism versus siblings by stating it 'Uses only the coarse location metadata ChatGPT shares,' which differentiates it from find_churches_in_city (likely city-based) and get_church (likely specific lookup). No ambiguity remains.

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 clear applicable context: use when location comes from ChatGPT's coarse metadata, not raw input fields. It explains behavior when the metadata is city-only. Although it does not name alternative sibling tools or exclusions, the context is explicit enough for an agent to decide when to invoke this 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?

Annotations already indicate readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds useful behavioral context by enumerating the fields returned (worship styles, denomination, language, etc.) and notes availability depends on 'if available.' No contradictions 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?

A single, well-structured sentence that front-loads the core purpose (get profile by slug) and then lists relevant output fields. No filler or redundant content; every clause adds value.

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 one clearly documented parameter, annotations for read/destructive behavior, an output schema, and sibling context, the description fully supports correct invocation. It covers the key inputs, expected output, and differentiation from related tools.

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 covers the slug parameter (100% coverage) with an example. The description adds extra semantic value by explaining the slug is the last path segment of a specific URL pattern, which is not in the schema. This helps the agent construct a valid slug.

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 states a specific action ('Get the full profile for one church') with a precise resource identifier (slug) and explicitly defines the slug via URL pattern. It clearly distinguishes from siblings that search/find churches by listing the profile contents, so an agent can select it without ambiguity.

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 makes clear this tool is for retrieving a single known church profile via slug. It does not explicitly mention when not to use it or direct to siblings for searching, but the sibling names and context imply that. Lacks explicit exclusions, yet the usage context is easily inferred.

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