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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds little beyond that—just the example key format which is already in schema. No mention of error handling, return structure, or edge cases. With annotations providing the safety profile, a score of 3 is appropriate as it adds minimal behavioral context beyond 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?

One sentence, clear and direct, no fluff. Front-loaded with the action.

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 parameter, safe read operation, no output schema. The description provides sufficient context for basic use, but could specify what 'detailed information' includes or mention error behavior. However, given the simplicity, it's fairly 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 covers the parameter fully with description and pattern. Description repeats the example but adds no new semantic information. With 100% schema description 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 clearly states the verb 'Get' and the resource 'detailed information for a specific author' using the Open Library key. It distinguishes from siblings like get_book_by_id and get_authors_by_name by focusing on the author key lookup.

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 when a known author key is available, but it does not explicitly mention when to use this vs. alternatives like get_authors_by_name. It provides context (the key) but no exclusion criteria.

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 readOnlyHint=true and openWorldHint=true, indicating safe read and possible missing data. The description adds that it reports when no photo exists, which aligns with openWorldHint and provides meaningful behavioral context beyond the annotations. This handles the missing photo case explicitly, which is valuable for agents.

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, front-loaded with the core function ('Get the URL'), and each sentence provides essential detail (ID format and missing-photo behavior). No wasted words.

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 (single param, no output schema), the description is highly complete. It covers the purpose, the ID, and the edge case of missing photosabbia. While it doesn't mention return format, the lack of output schema means it's not required, and annotations cover safety aspects.

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 coverage is 100% and the schema already describes the olid parameter. The description's example (OL23919A) reinforces the format and makes it clearer for agents, adding value beyond the schema. This is effectively a baseline 3 with a bonus for the example, and given the high coverage, it's sufficient.

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 it gets the URL for an author's photo, specifying the resource (author's photo) and the required identifier (OLID), and even includes an example. It distinguishes itself from siblings like get_author_info and get_book_cover by focusing specifically on photo URLs and handling missing photos.

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 when to use this tool (when needing an author's photo URL) and provides guidance on the ID format, but it does not explicitly state when not to use it or mention alternatives. Since there are sibling tools like get_author_info that might also provide photo info, explicit exclusions would help, but the context is clear enough.

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 and openWorldHint, and the description adds useful behavioral details: result cap, default limit, total match count via num_found, and pagination behavior. It does not mention rate limits or auth, but for a read-only search tool the disclosed behavior is sufficient and does not contradict 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 concise sentences contain all essential information: search scope, result cap, default, total count, pagination, and integration with a sibling tool. Every phrase earns its place with no filler or repetition.

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 with three parameters and no output schema. The description fully compensates for the lack of an output schema by explaining the return shape, count field, pagination parameters, and next-step usage with get_author_info. It is 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 coverage is 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema by explaining how limit and offset interact with pagination, defining num_found, and showing how the returned key connects to get_author_info. This adds value rather than just restating schema fields.

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 action: 'Search for author information on Open Library.' It clearly identifies the resource (authors) and distinguishes itself from sibling tools like get_author_info and search_books by describing a list-returning search behavior with pagination.

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 usage context: it returns a list up to a limit, supports pagination via offset, and explicitly tells the agent to pass a result's key to get_author_info for the full record. It does not explicitly state when not to use this tool versus alternatives, but the follow-up instruction provides practical 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 already disclose readOnlyHint=true and openWorldHint=true, covering the core safety profile. The description adds only the vague promise of 'detailed information' and does not disclose response structure, error behavior, or identifier-format nuances, though 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 a single, front-loaded sentence with a clear verb and resource. It contains no wasted words and efficiently conveys the core 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?

For a simple two-parameter lookup with full schema coverage and relevant annotations, the description is adequate. It does not detail the return shape, but this is a minor gap given the tool's simplicity and the absence of an output 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 100%, with both parameters fully documented including the idType enum and case-insensitivity. The description merely restates the identifier types that are already present in the enum, adding no new semantic detail.

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 ('Get'), identifies the resource ('detailed information about a book'), and specifies the lookup method ('using its identifier'). This clearly differentiates it from sibling tools like get_book_by_title or search_books.

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 implies the tool should be used when an identifier (ISBN, LCCN, OCLC, or OLID) is available. It does not explicitly name alternatives or exclusions, but the identifier-based context is sufficient to guide selection.

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 indicate read-only and open-world behavior, so the description adds value by explaining pagination mechanics (limit, offset, num_found) and result structure (best_edition with ISBNs and edition_key). This goes beyond the schema to give a clear mental model of the tool's 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 description is three sentences, front-loaded with the core purpose, and each subsequent sentence adds meaningful operational detail. No redundant or promotional 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, the description does a good job of explaining the return structure (num_found, best_edition, ISBNs, edition_key) and how it relates to another tool. It is complete enough for an agent to understand what to expect, though it omits details about other fields or search sorting (likely not essential).

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. The description enhances parameter understanding by explaining how limit, offset, and num_found work together for pagination, and by describing the semantics of edition_key. This adds value beyond the schema's field-level descriptions.

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 action ('Search for a book by its title') on a specific resource (Open Library). It clearly distinguishes from siblings by focusing on title-based search, and the cross-reference to get_book_by_id further clarifies its role.

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 usage context: search by title with pagination controls. It also provides a concrete alternative path by noting that edition_key can be passed to get_book_by_id for full records, which helps agents choose between tools. However, it does not explicitly contrast with search_books or state when not to use this tool.

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?

The description adds behavior beyond the readOnlyHint and openWorldHint annotations by stating it 'reports when no cover exists rather than returning a URL to a blank placeholder.' This is a valuable edge-case disclosure not captured elsewhere, though it doesn't cover other potential behaviors like rate limits or authentication.

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-loads the action and input types, and contains no redundant phrases. Every word contributes to understanding the tool's function and behavior.

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 (3 parameters, no output schema, read-only annotations), the description adequately covers the purpose, identifier types, and a key edge-case (no cover). It could mention the size parameter or URL format, but those are already in the schema, so it feels complete enough.

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 input schema already provides 100% coverage with detailed descriptions for all three parameters, including enums and defaults. The description only repeats the key types (already in schema) and adds no additional semantic meaning beyond what is structured, so the baseline of 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 clearly states the tool retrieves a cover image URL using a specified key type and value. It specifies the exact identifier types (ISBN, OCLC, etc.), and the verb 'Get' with resource 'URL for a book's cover image' distinguishes it from sibling tools like get_book_by_id or search_books.

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 provides context on when to use the tool by listing the required identifier types, but it does not explicitly contrast it with alternatives or state when not to use it. The purpose is clear enough that an agent would infer usage for cover retrieval, but explicit exclusions are missing.

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?

The description discloses detailed runtime behavior: result limit (default 10), num_found field, paging with offset, and the structure of each result (best_edition with ISBNs and edition_key). It also explains how to use edition_key with get_book_by_id. Since annotations already mark it as readOnly and openWorld, the description adds substantial value by explaining pagination and result format, going 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?

The description is three sentences long, front-loaded with the purpose, then usage constraints, then result details. There is no fluff or repetition of schema information. Every sentence contributes meaningful information: what it searches, how to combine criteria, and what results look like including chaining. Efficient and well-structured.

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?

This is a complex tool with 12 parameters and no output schema. The description fully covers the essential aspects: search criteria, result limit, pagination, result structure (best_edition), and how to access full records via edition_key. It leaves no major gaps for an agent to invoke the tool correctly and interpret results. The coverage is comprehensive given 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 input schema covers 100% of the 12 parameters with descriptions, so the baseline is 3. The description adds semantic context by listing searchable criteria, explicitly stating the requirement of at least one criterion, and explaining how combining them narrows results. It also clarifies the meaning of limit and offset in the context of num_found and paging, which is not fully captured in the schema. This adds value beyond the schema descriptions.

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 exactly what it does: 'Search Open Library across titles, authors, subjects, places, people, publishers and ISBNs.' The verb 'search' plus the specific resource ('Open Library') and the enumerated fields make the purpose unambiguous, and it clearly distinguishes from sibling tools like get_book_by_id (which retrieves specific records) by focusing on search across multiple criteria.

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 clear usage context: 'Provide at least one search criterion' and 'combining several narrows the search.' It also explains paging with offset and chaining to get_book_by_id via edition_key. However, it does not explicitly mention when not to use this tool or contrast it with alternatives like get_book_by_title, though the chaining hint implies an alternative path. The guidance is strong but not fully explicit about exclusions.

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