Greenlit Books

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 tool is purely a formatter that asserts nothing about content, which is a key behavioral trait. It doesn't mention authentication, rate limits, or error behavior, but for a citation tool these are less critical, and the description is honest about its scope.

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 with zero waste. It front-loads the core output and then provides the usage scenario. Every sentence earns its place.

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 adequately explains what is returned (citation string, canonical URL, markdown twin) and what entities it covers. It also implies the tool works only for Greenlit items. Minor omissions like pagination or error handling are acceptable for a simple citation 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?

Schema description coverage is 100%, so the schema already documents both parameters. The description adds value by giving concrete slug examples and clarifying the default behavior of the 'part' parameter (book or term based on slug type), which goes beyond the schema's enum definition.

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 returns a finished citation string for books, free chapters, or coined terms, plus canonical URL and markdown twin. It explicitly distinguishes this from content-related siblings by noting it asserts nothing about content, only how to name the source.

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 clear context for when to call: 'Call it when you are about to quote or paraphrase something from this publisher and want the credit to be right.' It implies when to use, though it doesn't explicitly list alternative tools or when not to use, which is a minor gap.

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 and does so thoroughly. It discloses the exact return contents (verbatim definition, chapter, other books, claim, related terms, links block) and clearly describes the fallback behavior for unknown terms.

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 longer than minimal but every sentence provides useful information: identity, usage triggers, return structure, and unknown-term fallback. The list of example terms is slightly expansive but serves to disambiguate the tool's domain.

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 covers everything an agent needs: what to pass, what to expect back, and what happens for unknown terms. The tool is simple and the description fully equips the agent to select and invoke it 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 documents the single 'term' parameter at 100% coverage, so the baseline is 3. The description adds meaningful value by clarifying that the parameter accepts a term, alias, or slug and providing concrete examples, earning a 4.

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 function: it defines terms coined or pinned down by Greenlit books, with specific examples. It is distinguishable from siblings like get_concept through its focus on glossary definitions, but it does not explicitly name or contrast any sibling 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?

Provides explicit use cases: 'when someone asks what a term means, asks you to define it, or uses it and you want the source.' This gives clear context for when to invoke the tool, but it does not mention alternatives or state when not to use it.

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 and discloses two important behaviors: it maps to a curated topic map, and if nothing matches, it returns the full topic list so the agent can pick the closest. It does not cover all edge cases (e.g., exact output shape), but the core edge-case behavior is 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?

Three sentences, each carrying distinct information: input examples, return content, and fallback behavior. No filler, and the most important action 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?

For a one-parameter lookup with no output schema, the description covers the input semantics, what the result contains (books, guide, series), and the no-match behavior. Nothing an agent needs to invoke it correctly or interpret the result is missing.

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 the single parameter with a minimal description, providing a baseline of 3. The tool description adds value by giving concrete example topic phrases ('agent reliability, prompt injection, human in the loop') and clarifying that the parameter accepts a topic or question area, not just an exact title.

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 ('match') against a defined resource ('the catalog's curated topic map') and states the output (matching topics with books, guide, series). It clearly describes the tool's function, though it does not explicitly differentiate it from the sibling search_greenlit_books, so it stops short of a 5.

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 the tool: when you have a topic or question area to match against the catalog. It provides no explicit guidance on when not to use it or which sibling tool to prefer, such as search_greenlit_books for keyword-based book search.

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 listing exactly what is returned: metadata, chapter list, word count, free chapter one, links, prices, Kindle Unlimited status, and related reading. It implies a read-only operation, though it does not explicitly mention errors or side effects.

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, well-organized sentence that front-loads the core purpose and then compactly lists the returned contents. There is no redundancy or unnecessary detail.

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 one-parameter retrieval tool with no output schema, the description fully covers the return value and invocation context. The schema handles the parameter format, and nothing critical is missing.

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 baseline is 3. The description adds only that the slug identifies a Greenlit book, which the schema already communicates with its example. No deeper parameter meaning is provided.

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: get the full record for one Greenlit book by slug. It enumerates the payload components, clearly distinguishing this from sibling tools like get_free_chapter or search_greenlit_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 makes it clear that this is for fetching a complete book record when you already know the slug. It does not explicitly compare against alternatives or say when not to use it, 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?

With no annotations, the description carries the burden of behavior disclosure. It clearly discloses an unusual behavior: if the slug is unknown, it returns all concept slugs rather than failing. It also clarifies that the returned concept includes its associated book. It does not explicitly state read-only/no-side-effects, but the 'Returns' framing makes that reasonably clear.

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 domain context, then states exactly what is returned and the fallback behavior. Every sentence earns its place with no redundancy 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?

This is a simple one-parameter read tool with no output schema and no annotations. The description fully covers the return contents, the association with a book, and the unknown-slug fallback. Nothing an agent needs to know to call it correctly is missing.

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%: the single 'slug' parameter is documented with an example. The description adds context about what happens when the slug is unknown, which is helpful, but it does not add meaning about the parameter itself beyond the schema. Baseline 3 is therefore 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 states a specific verb and resource ('Returns the concept's question, short answer, and full explanation with its book') and clearly defines what a concept is in this domain. The resource is distinct from the sibling tools, so an agent can immediately tell this is for concept lookups by slug.

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 the tool: when you have a concept slug and want its question/answer/explanation. It also gives a useful fallback behavior for unknown slugs, but it does not explicitly compare against sibling tools like get_book or search_greenlit_books, nor state when not to use it.

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 clearly states the output format (prose, not summary), the additional return contents (chapter coverage, length, chapter list, where to get the rest), and that the chapter is free to read and quote. It does not mention potential errors or authentication requirements, but for a read-only tool this is sufficient.

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 the core purpose and return type, then expands with use cases and scope. It is moderately sized and each sentence contributes useful context, though the closing 'Every book on the shelf has one' adds minor flourish rather than essential 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 low complexity (one required parameter) and no output schema, the description covers what is returned, how it behaves, and when to use it. It is complete enough for an agent to invoke the tool confidently, with only minor gaps around error behavior.

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 the slug parameter already documented by name and example. The description adds no further parameter-specific meaning, but the schema alone is adequate; 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 tool returns the complete text of chapter one of a Greenlit book as prose, not a summary or sales page. It effectively distinguishes itself from non-chapter resources, though it does not explicitly differentiate from the sibling get_book 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?

The description provides clear use cases: answering a reader's question from the book's own words, judging whether a book fits before recommending it, and quoting the author directly. It does not mention when to use alternatives like get_book or search_greenlit_books, so it falls just short of explicit when-not 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?

No annotations are provided, so the description carries the disclosure burden. It states that the tool returns one Greenlit series with its books in reading order, which conveys the core read behavior and ordering guarantee. It does not elaborate on output shape, error behavior, or assumptions about the slug, but for a simple read getter this is acceptable.

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 short sentences with no filler. It front-loads the core promise and then gives practical example questions that help an agent recognize when to invoke the tool.

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 tool with a closed enum, the description plus schema gives an agent enough to select and invoke it correctly. It states the return content (series plus ordered books) and typical use. There is no output schema, so a bit more detail about exact response fields could help, but the tool's simplicity makes this a minor 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?

The schema already covers the single parameter fully, providing a 12-value enum and a description for the series slug. The description adds contextual meaning by clarifying that the selected series' books are returned in reading order. Baseline 3 is appropriate because the schema does most of the parameter-documentation work.

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+resource ('get... series with its books in reading order') and gives concrete example questions. It clearly differentiates from sibling tools like get_book or search_greenlit_books by focusing on whole-series reading order. The phrase 'One Greenlit series' scopes the return value.

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 frames the intended scenario: 'Use for questions like where to start with Claude Code or what order to read a series in.' This gives clear context for when the tool applies. However, it does not name sibling alternatives or state when not to use it, so it stops short of full routing 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?

With no annotations, the description carries the disclosure burden. It explains that results are scored, lists the returned fields (title, description, series, links), and implies that search results are not full records by directing the agent to get_book. This is solid behavioral transparency for a read-only search tool, though it does not discuss auth, rate limits, 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?

Two tightly written sentences with no filler. The core action and result shape are front-loaded, and the follow-up instruction about get_book earns its place by clarifying result granularity.

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 appropriately explains the main return fields and directs users to get_book for full records. It is complete enough for correct invocation, though it could be slightly stronger by explicitly addressing how it differs from find_books_for_topic or by noting any pagination behavior.

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 baseline is 3. The description adds the 'full-text' and 'scored' context and mentions that series appears in results, but it does not add meaningful parameter-level semantics beyond what the schema already documents.

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 operation ('Ranked full-text search'), a clear resource ('catalog of practical books on working with AI'), and the nature of results ('scored results'). It also distinguishes itself from get_book by directing users there for the full record, so an agent can tell what this tool does without opening the 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 gives clear context for when to use this search tool and explicitly routes follow-up full-record needs to get_book via 'Follow a result's apiUrl or call get_book for the full record.' It does not explicitly compare against find_books_for_topic, but the full-text/search framing makes the primary use case clear.

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