corpus

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that rows are source-grounded, include links to digitized texts, and that no interpretation is applied. It also notes licensing (CC0) and alternative hosting (Hugging Face/Kaggle). It does not mention pagination or rate limits, but for a read-only comparative table tool, this is adequate transparency.

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 compact—three sentences total—and front-loaded with the core purpose. It packs dataset options, content characteristics, source links, interpretation stance, licensing, and external availability without redundancy. Every clause contributes useful 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?

Given the tool's simplicity (2 params, no output schema, no annotations), the description covers purpose, dataset selection, content nature, and licensing. It could explicitly mention returning rows with source links, but that is implicitly covered. It lacks details on pagination or output format, though the absence of an output schema makes this less critical. Overall, it is sufficiently complete for an agent to invoke 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?

The schema already provides 100% coverage for the two parameters with clear descriptions (e.g., filter as case-insensitive substring, dataset enum). The description adds value by detailing the internal structure of at least one dataset (flood-myths columns) and clarifying the thematic scope of each dataset, helping the agent choose appropriate dataset values.

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 'Return rows from one of the Wheel of Heaven comparative-mythology datasets', a specific verb+resource pair, and enumerates the five datasets with detailed examples (e.g., flood-myths columns). This clearly distinguishes it from sibling tools like get_entry, get_interpretation, or search_corpus, which handle single entries, interpretive content, or broader search.

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: it is for accessing comparative, source-grounded mythology tables without interpretation, which contrasts with get_interpretation. It names the dataset categories and their contents, giving a clear sense of when to choose this tool over siblings, though it does not explicitly state exclusions or alternatives.

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 no annotations provided, the description carries the transparency burden. It discloses key behaviors: returns markdown, includes specifically named metadata fields (claim_type, editorial_pass, references, typed related-content edges, canonical citation URLs), and truncates long bodies unless full_body=true. It also defines claim_type values. This goes well beyond the schema, though it does not mention error handling or edge cases.

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 compact but information-dense. It packs a full sentence listing metadata fields and explaining claim_type, plus another on truncation. Every clause adds value, though it runs long enough that a 5 would require tighter phrasing. The structure is logical: primary purpose, then return format, then behavioral caveat.

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 complexity (four sections, metadata, language fallback, truncation) and lack of output schema, the description explains the return format and key behaviors sufficiently. It does not describe error cases or the exact shape of related-content edges, but for a fetch-one-entry tool it is reasonably complete and would guide an agent effectively.

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 already provides 100% coverage of the four parameters, so the baseline is 3. The description adds significant meaning beyond the schema by explaining the structure of the returned metadata and the truncation/full_body behavior, which clarifies how the parameters affect output. It does not repeat parameter syntax but enriches the semantic context.

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 ('Fetch') and clearly identifies the resource ('one Wheel of Heaven entry') with examples of the four content types. It distinguishes itself from sibling tools like get_source or get_passage by focusing on the unified entry object with its epistemic metadata.

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 establishes clear context: this tool fetches a single entry by section and slug. It implies usage when a complete entry with metadata is needed, and the schema notes 'find slugs via search_corpus' for discovery. However, it does not explicitly state when to prefer this over alternatives or when not to use it, so it falls short of a full 5.

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 no annotations to help, the description discloses the output ('definition and renderings in all 9 site languages') and the optional-parameter behavior ('Pass no term to list all glossary terms'). The verb 'Look up' and the 'get_' prefix imply a non-destructive read operation, though it does not discuss rate limits or error conditions. For a simple lookup, this is adequate.

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 sentences, no filler. The first sentence states the action, resource, and output; the second explains the no-argument behavior. Each phrase adds useful information: examples, site-language count, and the list-all-terms option.

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?

The tool is simple (one optional param, no output schema), and the description adequately covers both input modes and the return content (definition and translations). It also distinguishes itself from siblings by scoping to 'project glossary', leaving no meaningful gaps for the tool's 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?

The schema already fully documents the single optional parameter 'term' (type, description, and omit-to-list-all behavior). The description adds examples (Elohim, Yahweh, precession, World Ages) and the 'core Wheel of Heaven term' context, providing marginal added value. With 100% schema coverage, baseline 3 is appropriate.

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 'Look up' and identifies the resource: 'a core Wheel of Heaven term ... in the project glossary'. It names examples (Elohim, Yahweh, precession, World Ages) and clearly distinguishes from sibling tools by scoping to 'project glossary' rather than entries, passages, sources, or traditions.

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 its use case: when you need a glossary term's definition and translations. It also states the no-argument behavior ('Pass no term to list all glossary terms'), giving clear context. However, it does not explicitly mention alternatives or when-not-to-use, so it falls short of a 5.

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 no annotations provided, the description carries the full burden. It discloses the interpretive bias (Raëlian-canon-centred), what it returns (framework reading), and its behavior for arbitrary topics (closest wiki entry). It also states what it does not do (source-grounded data). This is strong transparency for a non-mutating lookup tool.

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, each with a distinct purpose: core purpose, accepted inputs/behavior, and alternative tools. The description is front-loaded with the main action and maintains high information density without fluff.

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 a single parameter and no output schema, the description provides sufficient context for selection and use. It explains the interpretive nature, the input domain, and when to choose sibling tools. No critical information is missing for an agent to decide 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?

Although the schema has 100% coverage of the only parameter 'topic', the schema description is minimal. The tool description enriches semantics by enumerating specific framework topics (overview, hypothesis, terminology, timeline, sources, method) and explaining the fallback behavior for any other term. This goes beyond the schema's basic description.

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 verb ('Return'), resource ('Wheel of Heaven interpretive framework's reading'), and scope ('of a topic'). It explicitly distinguishes from mainstream consensus and distinguishes itself from sibling tools like get_passage and compare_traditions, which provide fact-layer data.

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 provides explicit when-to-use guidance: use for the framework's interpretive reading. It also gives an explicit alternative: 'Use fact-layer tools (get_passage, compare_traditions) for source-grounded data without this framing.' This clearly differentiates from the listed 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?

With no annotations provided, the description assumes the full burden of behavioral disclosure. It clearly specifies the content returned (taxonomy, six-source rule, editorial passes, translation policy) and its role in interpretation. It does not mention side effects or return format, but for a read-only informational tool this is adequate and adds meaningful context beyond a simple 'get method' label.

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 sentences, highly efficient. The first sentence delivers the core purpose and lists the specific content areas. The second sentence provides the usage directive. Every word earns its place, and the key 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?

Given the absence of an output schema and parameters, the description fully covers what the tool returns and why to call it. It enumerates all major components of the methodology and gives the agent a clear reason to use it alongside the sibling tools. No significant gaps remain.

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 the baseline is 4. The description adds meaningful context about the fixed scope of the output, which is useful. No parameter documentation is needed because there are none.

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 the explicit verb 'Return' and names the exact resource: 'Wheel of Heaven editorial methodology.' It goes further to enumerate the taxonomy levels and the six-source rule, making it unmistakably distinct from sibling tools that retrieve entries, passages, or sources.

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 this tool: 'Call this to understand how to weigh everything else this server returns.' This provides a strong usage context. It doesn't explicitly mention when not to use it, but it implicitly positions itself as the foundational reference tool among siblings, so the guidance is reasonably complete.

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 no annotations provided, the description carries the full burden and does well: it discloses that results are 'numbered paragraphs with stable reference IDs', that filtering by ref is optional, and that 'English editions in v1'. These are behavioral details beyond the schema, though it doesn't describe error handling or the exact response structure.

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 deliver purpose, examples, scope, disambiguation, lookup guidance, and version note. Every sentence earns its place with no redundancy or filler. The structure front-loads the primary action and then adds supporting context.

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 straightforward get tool with no output schema and no annotations, the description covers the essential context: what it fetches, how results are formatted, how to filter, how to find book slugs, and what edition is available. It doesn't mention pagination or limits, but those are less critical for this tool type. Overall, it is adequately 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 book, chapter, and ref adequately. The description adds a concrete example ('GEN-1:26') and clarifies that book slugs come from search_corpus, but it doesn't significantly expand on the schema's parameter documentation. Baseline 3 is appropriate.

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 the specific verb 'Fetch' and names the resource: 'a chapter of a digitized primary source text from the Wheel of Heaven library.' It provides concrete examples of source texts and stable reference IDs, and explicitly distinguishes itself from interpretation tools ('it returns the text itself, not interpretation'). This clearly differentiates it from siblings like get_interpretation.

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 guidance by labeling itself 'the primary-source tool' and contrasting with interpretation. It also tells users to find book slugs via search_corpus, which is a direct prerequisite. However, it doesn't explicitly mention when to avoid this tool in favor of get_source or compare_traditions, so while context is clear, explicit exclusions are absent.

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 no annotations provided, the description carries the full burden. It discloses that the bibliography deliberately includes critical and skeptical sources and that every record carries classification fields (source_family, stance, relation_to_wheel). This adds useful behavioral context beyond the schema, though it omits behavior when both id and query are provided or when no parameters are supplied.

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, front-loaded with the general purpose, then details the two usage modes. Every sentence contributes value with no redundant or filler language.

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 no output schema and three optional parameters, the description covers the return record fields (description, author, publish date, licensing, link) and the classification fields, making it fairly complete. The only notable gap is the behavior when multiple parameters are used together or when none are passed.

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 already has 100% coverage, but the description adds meaning by explaining that id retrieves a full source record while query searches across title/family/stance. It also lists the contents of a full record, enriching the parameter-level descriptions from 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?

The description states a specific verb 'Look up' with a distinct resource 'Wheel of Heaven bibliography (source program)'. It clearly differentiates from sibling tools by focusing on the source program/bibliography, and outlines two modes: id lookup and query search.

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 explicitly explains when to use each mode: pass id for a full record, pass query to search by title/family/stance. It provides context about the record classification and the deliberate inclusion of critical sources, but it does not explicitly name alternatives or exclusions, so it falls short of a 5.

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 no annotations, the description carries the full burden of explaining behavior. It does this well by disclosing the 1-hop limit, bidirectional edges, typed edge list, and resolved neighbor titles/URLs. It does not mention error handling, auth, or rate limits, but for a read-only graph query, this is reasonably transparent.

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 long and front-loaded with the core purpose. Every clause adds value: the graph type, the 1-hop ego network, the typed edges, both directions, resolved titles/URLs, and a usage hint. There is no wasted text.

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 tool with no output schema and no annotations, the description covers the essential return behavior (edges, directions, resolved titles/URLs) and provides a practical use case. It lacks explicit notes on empty results or errors, but the description is sufficiently complete for an agent to select and invoke 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 100% for all three parameters, so the baseline is 3. The description adds minimal extra meaning beyond the schema, such as clarifying that slug and section identify a node and that edge_type filters edges. It does not expand on parameter syntax or provide examples beyond the schema itself.

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 identifies the tool as a query operation on a typed content graph, specifying the exact resource ('typed Wheel of Heaven content graph') and the scope ('1-hop ego network of any corpus node'). It also lists the edge types explicitly, distinguishing it from sibling tools like search_corpus or get_entry.

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 states when to use the tool: 'finding everything connected to a concept, or how two entries relate.' This gives clear context, though it does not explicitly exclude alternatives or mention when not to use it. It implies these use cases separate it from searching or retrieving single entries.

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 no annotations provided, the description carries the full burden of behavioral disclosure. It explains the output (ranked matches with slugs and URLs), the licensing/CC0 status, and the scope of sources searched. This goes beyond a simple 'searches this corpus' statement, though it omits potential details like rate limits or pagination.

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 sentences long, front-loads the core search function, and every sentence adds value (scope, output, follow-up instruction, licensing). There is no redundancy or fluff.

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 tool with three optional-ish parameters and no output schema, the description covers the essential context: what's searched, what's returned, and how to retrieve full entries. It is sufficiently complete for an agent to select and invoke 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?

The schema covers all three parameters with descriptions and an enum for section, but the description adds semantic value by providing example queries, elaborating on the library content (naming specific texts), and clarifying that omitting section searches everything. This enhances the schema's information.

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 a full-text search tool over specific named sections of a corpus, with a specific verb ('search') and resources (wiki, timeline, library, articles, news). It distinguishes itself from siblings like get_entry and get_source by stating it returns ranked matches with slugs and URLs.

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 explicitly mentions using get_entry to fetch full content after search, which gives a clear alternative for the follow-up step. It does not enumerate all when-not cases, but the context strongly implies search is for discovery and get_entry is for retrieval, providing sufficient guidance.

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