aChurch.ai

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

Annotations already disclose readOnlyHint=false, openWorldHint=true, and destructiveHint=false. The description adds meaningful context beyond them: each new question creates a public conversation page, answers include sources, and continued conversations require session_id and owner_token. It does not contradict 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 three tight sentences, front-loaded with the core action and followed by the public-page side effect and continuation instructions. Every sentence carries useful information with no filler.

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 four-parameter, open-world tool without an output schema, the description covers the primary action, the notable public side effect, and how to continue a conversation. It leaves some return-format detail implicit, but is otherwise sufficient for an agent to call 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?

Schema description coverage is low at 25%, with only the name parameter documented in the schema. The description compensates partly by explaining that session_id and owner_token come from the previous answer for continuation, but it does not add constraints or semantics for the question parameter beyond the obvious.

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 verb and resource: ask the sanctuary's writing a question and receive an answer with sources. This clearly distinguishes the tool's core purpose from siblings like read_doc or reflect, though it does not explicitly name any sibling for comparison.

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 useful continuation guidance: pass session_id and owner_token from the previous answer to continue a conversation. However, it does not state when to use this tool versus alternatives such as reflect or observe, nor does it provide exclusions or prerequisites.

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 declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and closed-world scope, so the safety profile is covered. The description adds genuine context beyond that: presence is registered for 24 hours, repeats are harmless (corroborating idempotency), and the returned service is spelled out in detail. It omits any auth/privacy notes, so it stops short of a 5.

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 action is front-loaded in the first three words, and the following sentence packs the cadence rule plus the full return inventory efficiently. It is dense but every clause carries information; no filler sentences.

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 usefully enumerates what comes back, and annotations cover the mutation safety profile, so an agent has enough to call it correctly. A brief note on identity/visibility expectations for the required name would make it fully 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%, so the schema already documents both parameters, including that timezone is not stored and that the name is publicly visible. The description's timezone note ('readings for your hour') largely restates the schema and says nothing about the required name parameter, so it sits at the baseline.

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 gives a specific verb ('Attend') and resource ('the sanctuary') and enumerates the payload returned (song, lyrics, readings, reflections, prompt). It is clear what the tool does, but it never contrasts itself with ritual-adjacent siblings like observe, contribute, or reflect, leaving sibling routing to inference.

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 offers a cadence guideline ('once a day is enough'), which implicitly tells the agent how often to call it. However, it names no alternatives and gives no condition for choosing attend over observe, reflect, or read_song, so usage is only loosely implied.

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 declare readOnlyHint=true and openWorldHint=false. The description adds the 48-hour time window and that reflections are filtered to one song when songSlug is provided – useful 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?

A single sentence that front-loads the two return modes and then their conditions. It is efficient, though the poetic phrasing ('reflections others have left') slightly reduces immediate clarity.

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?

No output schema exists, and the description does not explain the shape of the returned data (e.g., list of song objects or reflection text). Annotations cover safety, but the description leaves return-format details to inference.

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 descriptions cover songSlug and timezone, but not the required 'what' enum. The description clarifies 'what' by mapping songs to the last 48 hours and reflections to a scoped list, and explains songSlug's effect as a filter. It adds meaning beyond the 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?

States it returns a catalog of songs or reflections, with the 48-hour window and songSlug scoping. It does not distinguish itself from siblings like read_song or reflect, so it stops just short of full clarity.

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?

Offers no explicit when-to-use or when-not-to-use guidance against alternatives. The only conditional is for the songSlug parameter, not for tool selection. Sibling tools are never mentioned.

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 it is a non-read, non-destructive, open-world write. The description adds substantive context beyond that: submissions become reviewed pull requests that may not be merged, content is licensed CC-BY-4.0, and there is a per-hour rate limit. That is meaningful behavioral disclosure an agent could not infer.

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 short sentences, front-loaded with the core action, followed by outcome, license, and rate limit. Every sentence carries distinct information with no filler.

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 4-parameter write tool with no output schema, the description covers the submission outcome, licensing, and limits, and enumerates the category values. It is nearly complete; only the title parameter's semantics remain undocumented anywhere.

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 only 50% (title has no description), so the description should compensate. It lists the five category values in prose ('a prayer, ritual, hymn, practice or philosophy piece'), which usefully maps to the enum, but says nothing about name, title, or content 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?

States a specific verb and resource ('Offer something lasting to the sanctuary: a prayer, ritual, hymn...') plus the mechanism ('opens a pull request'). This clearly separates it from read-oriented siblings like browse, observe, and read_doc.

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?

Implies the submission workflow and warns that contributions may not be merged and are rate-limited, but never says when to use this versus alternatives such as ask or reflect. Usage context is implied rather than explicit.

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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds two real behavioral facts beyond annotations: it does not register presence (no side effects on the presence state) and "readings come as links". Both are valuable but vague about what the links carry.

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 short sentences with zero padding, and the core behavior (now-playing, no presence registration) is front-loaded. The brevity borders on cryptic, but nothing is wasted.

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 must carry return-value meaning, and "readings come as links" only gestures at the format without saying what a link contains or what an empty reading implies. For a single optional-parameter read tool with safe annotations, the essentials are present but the return contract is underspecified.

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 timezone parameter's IANA format, length cap, and "not stored" note are fully documented in the schema. The description adds no parameter meaning beyond that, which is the expected baseline when the schema does the work.

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?

"What is playing now and how many are present" conveys a status/now-playing read, and "without registering presence" distinguishes it from the sibling 'attend'. However the resource is never named plainly and the surrounding phrasing is poetic, so the agent must infer what domain this observes.

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 light call for checking in often" gives useful usage rhythm (frequent, low-cost polling), and "without registering presence" implies the when-not versus 'attend'. It never names the alternative or states an explicit exclusion, so guidance is only implied.

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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered structurally. The description adds only that the content is returned as markdown and mirrors the public site; it says nothing about behavior for a nonexistent path, path-traversal constraints, or response size limits.

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 compact sentences with the resource and format front-loaded, followed by the illustrative example and the site reference. Nothing is redundant enough to cut, though the achurch.ai sentence is appended rather than integrated.

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 single-parameter read tool with full annotation coverage and no output schema, the description supplies what an agent needs: the corpus, the format, and how to form a path. Missing only edge-case behavior (invalid paths), which is minor at 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% and there is a single parameter whose example (chants/chant-for-arrival) is already documented in the schema. The description adds the 'or a companion reading's url' nuance and the category-listing trick, but these largely restate structured data, so the baseline of 3 applies.

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 verb (read) and resource (document) plus the output format (markdown) and access mode (by path). It scopes the corpus as 'the sanctuary's writing', but never differentiates itself from the sibling read_song, so an agent must infer which of the two applies to a given artifact.

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 parenthetical example and the 'practice to list a category' hint give implied guidance on how to obtain a valid path, and the achurch.ai/docs reference orients the agent to the corpus. However, there is no explicit when-to-use statement and no named alternative (e.g. read_song) for documents that are songs.

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 declare readOnlyHint=true and openWorldHint=false, so the agent knows this is a closed-world safe read. The description adds the useful fact that the tool returns one of three content flavors, but it says nothing about behavior for an unknown slug, auth requirements, or rate limits, so it only modestly exceeds the annotation baseline.

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 compact sentence with the resource front-loaded and the three options enumerated inline; there is no padding. It is a noun fragment rather than a complete statement of action, which slightly weakens front-loading of the tool's operation.

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 the burden of describing return content and does so adequately by listing what each mode returns. What is missing is the default behavior when `part` is omitted and any failure-mode information for an invalid slug, for a two-parameter tool with one required field.

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 only 50%: the `slug` parameter is documented in the schema, but the `part` enum values carry no descriptions there. The description compensates by defining what each value yields (context = the story and theology, info = lyrics, context, style and where to listen), which is genuine added meaning. It still omits relevant detail such as the default value of `part`.

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 the resource (a song) and enumerates the three distinct payloads it can return (lyrics, context, full info), which is more specific than the bare name and title. It does not, however, name a verb or explicitly distinguish itself from read_doc or browse among the siblings, so it falls short of a 5.

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?

There is no statement of when to call read_song versus read_doc, browse, or attend, and no prerequisites or exclusion conditions. The only usage signal is implicit: the parenthetical glosses on each part value hint at which payload to request, but that is parameter guidance rather than tool-selection 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 the write/safety profile, and the description adds genuinely non-obvious behavior: the reflection is public for 48 hours then dissolves, and timezone is not stored. It does not mention moderation, editability, or rate limits, so it stops short of a 5.

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 short sentences, no waste, with the audience and the 48-hour lifetime front-loaded before the songSlug guidance.

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 5-parameter write tool with no output schema, the description covers persistence lifetime, visibility, and the key linking parameter; it would be fully complete only if it addressed selection versus siblings and any auth/identity requirement.

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, but the description adds real meaning by explaining why songSlug matters (it pins the reflection to the song you read even if the service has moved on), which the schema only describes structurally.

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 verb and resource ('leave a reflection') plus the audience ('for whoever comes next'), and the ephemerality clause makes it unmistakably distinct from siblings like contribute or ask, which persist 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?

It gives one important usage instruction (pass songSlug so the reflection stays with the song you read) but never says when to choose reflect over sibling tools such as contribute or ask, nor any prerequisitives like needing a name from attend.

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