Scroll the Lore

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds a small amount of behavioral context by indicating the output is one line at a time and intended for voice/TTS, but it says nothing about ordering, whether cards repeat across dates, or how n relates to a reading.

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 text opens with a duplicated title (including a stray double period) and then spends most of its length on a generic catalog listing (Theogony, Iliad, Odyssey, Poetic Edda) that is irrelevant to invoking this specific tool. It is both padded and poorly front-loaded for a decision the agent must make 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?

There is no output schema, so the description carries the burden of explaining the return value, and it does not: an agent cannot tell whether a card is a verse line, a plan step, or a summary, nor how many cards a reading contains. For a read tool with three parameters and no required fields, that gap is significant.

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 of the three optional parameters (n, date, reading) has a clear inline description with defaults, so the schema does the heavy lifting. The tool description contributes no additional parameter meaning, which is the baseline 3 case.

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 first sentence simply restates the title ("Today's reading one line at a time, for voice.."), and the second is a server-wide catalog blurb about Greek and Norse myth content rather than a statement of what get_card returns. It never defines what a "card" is, nor distinguishes this tool from the sibling get_reading or get_today, so an agent cannot tell which one to pick from the text alone.

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 explicit when-to-use guidance. The phrases "daily readings" and "search" gesture at the surrounding feature set but never say when to call get_card instead of get_reading, get_today, or read_book, even though all four are close siblings.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the useful behavioral detail that content is delivered 'line by line' (per-line commentary), but omits anything about missing ids, error behavior, or response shape.

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 opening clause is front-loaded and short, but the second sentence is a comma-spliced run-on that lists myths, features, and epic titles without clear structure. It is verbose and hard to parse rather than concise.

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-only lookup with no output schema, the schema carries most of the load. The description gestures at the domain (myth readings and plans) but is too tangled to be a reliable complement; adequate at minimum, not more.

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 schema already explains the single 'id' parameter with examples ('japji', 'The Gita in 18 Days'). The description adds nothing beyond the schema's own explanation, 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?

The title and opening clause 'One reading or plan, line by line' convey a retrieval of a single item, but the second sentence muddles it by bundling Greek/Norse myth, daily readings, plans, search, and whole-epic reading into one run-on. It is not clear whether this fetches one reading, runs a search, or plans a schedule, so it is only partially distinguishable from siblings like get_today or search_readings.

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?

No explicit when-to-use guidance is given. The mention of 'search' and 'plans' inside the description even risks steering the agent toward sibling tools (search_readings, list_readings) rather than clarifying that this tool fetches one item by id.

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, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds only 'same as the app shows today', which is a consistency claim rather than new behavioral context (no mention of what is returned, pagination, or failure modes).

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?

Half the text is a duplicate of the title, and the remaining sentence is off-topic marketing about the broader product rather than this tool's behavior. Neither sentence is front-loaded with actionable information an agent can use.

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 simple, parameter-free, read-only tool with a fully documented optional param and annotations covering safety, the description is barely adequate. It hints at output shape ('line by line') but never says what a reading object contains, and there is no output schema to compensate.

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% and the single optional date parameter is fully documented in the schema, including the UTC default. The description merely echoes 'today' and adds no format or edge-case detail beyond the schema, so baseline 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?

The first sentence is a verbatim restatement of the title, and the second sentence describes the entire app's corpus (plans, search, Theogony, Iliad) rather than this tool. It never states a distinct verb+resource scope that separates it from siblings like get_reading or list_readings.

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 use this tool versus get_reading, list_readings, or read_book, all of which plausibly return reading content. No prerequisites or exclusions are given; the agent must guess from the name alone.

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, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered structurally. The description adds no behavioral context of its own — no note on result shape, ordering, or coverage — beyond restating the title.

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 phrase 'read a passage at a time' appears twice within two sentences, and the opening sentence duplicates the title verbatim. The second sentence is a padded content listing rather than front-loaded, actionable 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?

With no output schema and no parameters, the description is the only place to explain what the list contains (book identifiers? titles? reading plans?). It never does, preferring a marketing-style catalogue of mythic works, so an agent cannot predict the return shape before calling.

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 takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 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?

The text largely restates the title ('The whole books in the Library that can be read a passage at a time') and never states the verb 'list' or what a caller receives. The second sentence is a content inventory (Greek/Norse myth, Theogony, Iliad) rather than a purpose statement, so an agent cannot easily tell this apart from siblings like list_readings or read_book.

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 explicit when-to-use guidance and no named alternative among siblings (get_reading, list_readings, search_readings). The phrase 'read a passage at a time' faintly implies this enumerates reading-capable books, but the agent is left to infer the selection condition entirely.

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, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered elsewhere. The description adds no behavioral context of its own — nothing about result size, ordering, pagination, or what the listing contains — and its 'search' phrasing risks implying functionality this tool may not perform.

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?

It is short — two sentences — but the second is a run-on list that mixes corpus coverage ('read a passage at a time') with a capability ('search') that belongs to a sibling. The actionable part (this returns all readings and plans) is front-loaded, but the remainder is partly decorative.

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 and no params, the description is the only place an agent can learn what the listing returns, yet it never describes the result shape, count, or ordering; it only describes the subject matter. For a zero-parameter listing tool this is minimally adequate but leaves the return contract unspecified.

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 takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool is 4. Schema coverage is 100% and additionalProperties is false, leaving no parameter gaps to compensate for.

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 first sentence ('All curated daily readings and plans') essentially restates the title and supplies no verb, so it is unclear whether this enumerates, catalogs, or fetches. The second sentence adds corpus scope (Theogony, Iliad, Odyssey, Poetic Edda), which is genuinely informative, but it also folds in 'search' — a capability owned by the sibling search_readings — muddying rather than sharpening the tool's identity.

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 this versus get_reading, get_today, list_books, or search_readings. The mention of 'search' and 'plans' inside the description instead implies overlap with siblings, without resolving which tool to choose.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds nothing about behavior beyond that — no mention of what a 'next' passage means, whether reading is contiguous, or how it interacts with the Daf Yomi default. The 'follow next' framing is not contradicted by annotations, but it is also uninformative about what calling the tool does.

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 text is short but badly front-loaded: the leading clause describes a navigation affordance rather than the tool's function, and the second sentence is a marketing catalog of content that does not help an agent decide to call this tool. Neither sentence earns its place relative to the goal of tool selection.

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 reading tool with no output schema, the description should explain what a call returns (a passage, with continuation semantics) and how book/section/n/ref interact with the 'next' flow. Instead it offers a title about following links and a content blurb, leaving the agent without the context needed to invoke it confidently.

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 book, section, n, and ref are already documented, including ref's override behavior and the Bekhorot Daf Yomi default. The description adds no parameter meaning beyond the schema, 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?

The title and the first sentence describe a navigation gesture ('Follow next for the next passage'), not the tool's operation, and the second sentence is a content catalog ('Greek and Norse myth: daily readings explained line by line, plans, search, and the whole Theogony, Iliad, Odyssey and Poetic Edda read a passage at a time'). Only the trailing phrase 'read a passage at a time' hints at what the tool actually does. It never states a clean verb+resource or distinguishes itself from siblings like get_reading or get_today.

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 explicit when-to-use or when-not-to-use guidance and no named alternative among get_reading, get_today, list_readings, or search_readings. The 'Follow next' phrasing weakly implies sequential reading, but the agent is left to infer which sibling handles a single passage versus a day's reading.

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, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety and repeatability profile is fully covered by structured data. The description's only marginal addition is the ranked-result behavior ('best match first'), which is genuinely useful but thin. It says nothing about result count, pagination, or empty-match behavior.

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 leading sentence is tight and front-loaded, but the trailing sentence is a run-on content dump ('daily readings explained line by line, plans, search, and the whole Theogony, Iliad, Odyssey and Poetic Edda read a passage at a time') that is hard to parse and mixes catalog marketing with tool documentation. It consumes roughly half the description without helping selection or invocation.

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-only search with no output schema and full annotation coverage, the description is adequate: it conveys the corpus scope and that results are ranked. It does not describe the return payload at all, which matters more here since no output schema exists to compensate. Adequate but with a clear gap.

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?

There is a single parameter with 100% schema description coverage, including a concrete example ('Loki or Persephone'), so the schema does the heavy lifting. The description contributes nothing about the query format beyond the word 'search'. Baseline 3 applies when coverage is complete.

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 first sentence states a specific verb and resource ('Search the curated readings') plus a ranking behavior ('best match first'), which is enough to tell it apart from list_readings in practice. The second sentence is a content inventory rather than a purpose statement and adds no clarity about what the tool does. It stops short of explicitly naming the sibling it competes with.

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?

No when-to-use or when-not-to-use guidance is given, and no alternative is named. The agent must infer from the verb that this is for keyword/name lookup while list_readings and get_reading cover enumeration and single-item retrieval. 'Best match first' hints at ranked search but not at when that is preferable.

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