The Old Ways Library

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

It provides specific context regarding the data's age by warning that the 'Index-build time is not the publication date of a historical text.' This is critical information that goes beyond what a simple 'list' function name or standard annotations would convey, helping the agent interpret the results correctly.

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 definition uses two well-structured sentences. The first defines the resource and its attributes, and the second provides a necessary caveat, ensuring that every word serves a functional or informational purpose.

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 zero parameter count and lack of output schema, the description is highly complete. It informs the agent exactly what data the tool will yield, allowing it to determine relevance and interpret results even without a formal return structure.

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?

Since there are 0 parameters and 100% coverage, the description is free of the obligation to compensate for missing schema details. It adds strong semantic value by listing all the specific data fields (traditions, source policy, content types) that the agent should expect in the response.

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 defines the purpose as listing available book landing pages and related metadata. It specifies exactly what information will be returned (landing pages, traditions, content types, etc.), making it 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 guides the user on when to use the tool, stating it should be used 'before exploring The Old Ways.' While it doesn't explicitly say 'use this before [sibling tool],' it clearly defines its role as a discovery/prerequisite step.

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?

With annotations already covering read-only, idempotent, non-destructive, closed-world behavior, the description adds useful context: bounded excerpts, citation URL and source note returns, nextOffset continuation, and caveats about transcription errors and editorial summaries. It also explicitly rules out arbitrary websites and private accounts, reinforcing the openWorldHint=false annotation.

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 usage, followed by return behavior and caveats. Every sentence adds useful information without repetition or 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 read-only tool with rich annotations and no output schema, the description covers purpose, return fields, scope restrictions, and source-quality caveats well. The main remaining gap is fuller explanation of the length and offset parameters.

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 0%, so the description must carry parameter meaning. It explains the required url as a canonical URL or path from search_library and implies offset through nextOffset continuation, but it does not clarify length units, defaults, or limits, leaving a clear gap for the optional length parameter.

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: read a bounded text excerpt from an indexed public theoldways.co page. It clarifies scope by naming the source domain and the need for a canonical URL or path returned by search_library, which distinguishes this from the sibling search tool.

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 clearly routes the agent to use a URL or path returned by search_library and states exclusions: no arbitrary websites, private accounts, or live app access. However, it does not explicitly describe when to use this versus list_collections or other alternatives beyond the URL requirement.

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 readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds real value beyond that: results come from a prebuilt lexical index, return canonical citation URLs plus short previews, and known malformed/noindex pages are excluded. It does not discuss result ordering or failure modes, keeping it 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?

Front-loaded with the resource scope, then the return shape, then the exclusion and sibling routing. Every sentence carries information, though the tradition list is somewhat dense and pushes the usage routing further down than ideal.

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 four parameters, the description does the necessary work: it explains what comes back (citation URLs, previews), signals the closed corpus, and routes follow-up to read_page. The only gap is the undisclosed `limit` parameter and its cap of 8, which an agent would have to read from the schema.

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 0%, so the description must carry parameter meaning. It partially does: the enumerated traditions map directly onto the `tradition` enum, and 'glossary, deity profiles and explanatory questions' hints at `kind` values. However `limit` is never explained and the `kind` enum values (chapter, book, reference) are not fully mapped, leaving the compensation incomplete.

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 (Search) plus the exact resource (the Old Ways historical-text and mythology collection) and enumerates the covered traditions and content types (glossary, deity profiles, explanatory questions). An agent can immediately distinguish this from a generic search tool or from sibling tools like read_page.

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?

Explicitly bounds the tool: 'Not web search or verification of historical claims' sets a negative condition, and 'Use read_page to examine the passage and recorded edition details' names the sibling that handles the follow-up step. This is a clear when/when-not/alternative triple.

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