Eremos Thai Bible

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 genuinely new context: output is word-for-word text with verse numbers and a link, and cross-chapter ranges are out of scope. It stops short of describing error behavior for unresolvable references.

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, zero filler, with the core purpose front-loaded and the format examples and scope constraint following. Every clause carries 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?

For a one-parameter read tool with no output schema, the description covers input formats, output shape (verse numbers plus link), and scope limits. Remaining minor gaps are error handling for invalid or cross-chapter references and any rate or availability caveats.

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% with a single parameter, so the baseline is 3, but the description goes further than the schema's one example by enumerating accepted forms: English or Thai book names, abbreviations, USFM codes, and ranges like 'Jn 3:16-18' and '1 Cor 13:4-7'. That materially reduces ambiguity about what the string may contain.

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: return the Eremos Translation (Thai) text of a Bible reference. It pins the scope ('one chapter or a verse range within one chapter') and is clearly distinguishable from siblings like search_text, list_books, and get_translation_notes.

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?

Usage is implied by the scope constraint (single chapter or intra-chapter range) and the accepted reference formats, but there is no explicit when-to-use guidance and no sibling is named as an alternative (e.g. search_text for topical lookup). Adequate but with clear gaps.

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 one useful behavioral fact — only 'published' decision records are returned, implying drafts are excluded — but says nothing about behavior when no note exists for a verse. Moderate value over 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?

Two sentences, zero waste. The return content is front-loaded and the usage condition follows, so an agent scanning the first clause immediately knows what it gets back.

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 fields, and it does so well (source words, Thai rendering, reason, notes). It omits only edge-case behavior (verse with no published note), which keeps it just short of 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 coverage is 100% and the single 'reference' parameter is fully documented in the schema with an example. The description only reinforces the cardinality constraint ('one verse'), adding little beyond what the schema already conveys; 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?

States a specific verb+resource ('Return the published decision record for one verse') and enumerates the payload: source words, Thai chosen, translator's reason, notes. It is easily distinguished from get_passage/search_text by content, though it never names a sibling explicitly.

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?

Provides a clear triggering condition ('Useful when a user asks why the Thai reads as it does'), which tells the agent exactly the user intent this tool serves. It gives no when-not guidance or explicit alternative routing, so it stops 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and scope are covered elsewhere. The description usefully adds that the result is a fixed, unfiltered set of 66 books with no parameters, which tells the agent to expect a complete static list, but adds little beyond that.

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 front-loaded sentence that names the resource and the exact fields returned, with no filler or redundancy.

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 compensates by enumerating the content of each record (English/Thai names, USFM code, chapter count), giving the agent enough to decide whether this call satisfies its data need. Nothing material is missing for a zero-parameter read-only list tool.

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 clarify; the baseline for a no-parameter tool applies. Schema coverage is also 100%, meaning structured fields carry any remaining burden.

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 (List) and resource (the 66 books) and enumerates the returned fields (English/Thai names, USFM codes, chapter counts). It is easy to tell apart from get_passage and search_text by function, though it never explicitly contrasts itself with those siblings.

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?

Usage is implied: this is the canonical reference list an agent should consult before calling get_passage or search_text with a book identifier. However, the description gives no explicit when-to-use statement, prerequisites, or named 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?

Annotations only declare readOnlyHint/openWorldHint; the description adds real behavior: conjunctive matching ('all words must appear'), the book scoping option, and the result shape ('up to limit verses with references') in the absence of an output schema. It stops short of describing matching mechanics (substring vs. word-boundary, Thai tokenization, ordering), which matters for unsegmented Thai text.

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, with the core search semantics and the AND-constraint front-loaded before the optional scoping and return-shape details.

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 return-value burden and does so adequately (count-capped verse list with references). For a simple three-parameter search it is essentially complete, with only result ordering/scoring left unstated.

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 67% — the 'limit' property has no schema description. The description compensates by explaining that results are capped at 'limit' and that 'book' optionally restricts the search to one book, effectively covering the undocumented 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?

States a specific verb and resource ('Find verses in the Eremos Translation whose Thai text contains the given words') and pins down the matching semantics with '(all words must appear)'. This clearly separates it from get_passage (retrieve a known reference) and list_books without opening either schema.

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 the use case (locate verses by Thai text, optionally scoped to one book) but never states when to prefer this over get_passage for a known reference, nor any exclusions. Usage is inferable but not spelled out.

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