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

Even with annotations declaring read-only, open-world, and idempotent behavior, the description adds substantial value: it reveals that the tool resolves the primary author, ranks by popularity, returns specific fields, paginates results, and caps limit at 100. These are non-obvious behaviors an agent needs to predict output.

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 and front-loaded: the purpose appears in the first sentence, and the following two sentences add only high-value behavioral details. No filler, no repetition of annotations or schema.

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?

Combined with the annotations and output schema, the description covers input semantics, output contents, pagination, and the limit cap. There is nothing essential missing 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?

Schema description coverage is 0%, so the description must compensate. It clarifies that book_id is a book identifier (not an author ID) and that limit is capped at 100 beyond its schema default. The id format and accepted values are not given, but core semantics are well covered.

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 ('List') and resource ('an author's works/bibliography') and makes the unique input clear ('given any of their books'). This distinguishes it from siblings like similar_books or series_books without needing to inspect their schemas.

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 trigger condition 'given any of their books' is clear, but the description never mentions alternatives or exclusion criteria. An agent must infer when to prefer author_books over similar_books or series_books, so guidance is implied rather than explicit.

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, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral detail beyond annotations: results are paginated in batches, the limit is capped at 100, and the ordering is by popularity. These are not inferable from the annotations or schema, making the description genuinely informative.

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 and front-loaded. The first sentence states the core purpose and ordering, followed by a sentence on output fields and use cases, then a final sentence on pagination and cap. Each sentence earns its place—no fluff or redundancy—and the structure allows an agent to quickly grasp what the tool does and its constraints.

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 list tool with two parameters and an existing output schema, the description is thorough. It covers the result fields (title, votes, book count, URL), the use case, the pagination behavior, and the cap. It does not need to explain return formats because the output schema handles that, and the annotations already cover safety, so 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?

The input schema has 0% description coverage, placing the burden on the description. While the description implicitly references book_id (the book in question) and mentions that 'limit is capped at 100,' it does not explicitly explain that limit controls the number of lists returned per batch, nor does it mention the default value of 10. This is partial compensation but not complete.

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 explicitly states the verb ('List'), the resource ('the Listopia lists a book appears on'), and the ordering ('by popularity'), with an example. This clearly distinguishes it from siblings like get_book (which fetches a single book) and similar_books (which suggest related works) without needing to open schemas.

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 on when to use the tool ('Good for "what kind of book is this / what's it grouped with" and for discovery'), which guides an agent toward appropriate scenarios. It does not explicitly name alternatives or state when not to use it, but the purpose is specific enough to avoid confusion with most 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?

Beyond the readOnly/idempotent annotations, the description discloses the ranking logic (best-to-worst by average rating), the computed percentages (pct_positive, pct_critical), and the refusal behavior for >10 ids. These are operational details an agent could not infer from the annotations or schema. No contradiction exists.

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, each with a distinct job: purpose, return semantics, and call limits. The most important information is front-loaded. No sentence is 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 one-parameter read-only tool with an output schema already available, the description covers invocation limits, return semantics, and the source of ids. Nothing needed for a correct call is missing. The output schema removes the need to enumerate returned fields in prose.

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 only provides a type and title for book_ids with 0% description coverage, so the description carries the explanatory burden. It supplies the valid count range (2-10), the refusal behavior, and the provenance ('from search_books etc.'). It does not define the exact id format, but for a single string-array param this is 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 opening sentence uses a specific verb ('Compare') and resource ('books') and immediately narrows the scope to rating and rating distribution. The second sentence specifies a ranked best-to-worst output, which differentiates it from sibling tools like get_book or similar_books. It even points at sibling search_books for id provenance, so an agent can select it confidently.

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 the intended call pattern: pass 2-10 book ids, and gives a hard behavioral rule for exceeding that range ('more than 10 is refused rather than silently trimmed, so split the call'). It does not explicitly enumerate when-not-to-use alternatives, so it falls just short of a full 5. Still, the context for when this tool is appropriate is unambiguous.

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 the safe read profile (readOnly, idempotent, non-destructive), and the description goes further by disclosing the parsing strategy (__NEXT_DATA__/Apollo state rather than DOM), the payload contents (ratings histogram, series memberships, review-language breakdown), and the default/max on review_language_limit.

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 id contract and tightly organized into three short paragraphs, each with a distinct job. The closing citation instruction is slightly tangential but short enough to justify 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?

With an output schema present, the description needn't enumerate return fields, yet it still names the notable payload sections. Combined with the id constraints, the alternative-tool routing, and the parameter semantics, nothing needed to call this 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 description coverage is 0%, so the description must carry the load, and it does: it defines book_id formats (numeric, numeric-slug, dot-slug) and describes review_language_limit's purpose, default of 5, and maximum of 25.

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 ('Get full details for a book') and immediately bounds the scope with the accepted id format. It also distinguishes itself from adjacent operations by clarifying that an ISBN is not a valid id and pointing to 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?

Explicitly says when this tool is the right one, gives the prerequisite ('find the book with search_books first'), and routes a sibling use case ('use get_reviews for the actual review text'). The agent has no guesswork left.

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, openWorldHint, idempotentHint, and destructiveHint. The description adds behavioral detail beyond that: results paginate in batches and limit is capped at 100. This is useful operational context not present in 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, front-loaded with the core action and followed by usage guidance and a pagination caveat. No 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?

With annotations covering safety/idempotency and an output schema present, the description covers purpose, usage, and pagination behavior. Nothing critical is missing for an agent to call 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?

Schema has 0% description coverage, so the description carries the burden. It clarifies that limit is capped at 100 and that results include formats/ISBNs/publishers/dates, which indirectly informs book_id output. However, it doesn't explicitly document the book_id parameter format or how limit interacts with pagination.

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 ('List') and resource ('published editions of a book'), then enumerates the data fields (formats, ISBNs, publishers, dates). This clearly distinguishes it from sibling tools like get_book (single book metadata) and search_books (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?

It states an explicit use case: 'which edition / format / ISBN' questions. It doesn't name alternatives or exclusions, but the context is clear enough for an agent to select this tool over 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds substantial behavioral context beyond annotations: true pagination allowing limit to exceed ~30, server-side star filters, spoiler exclusion behavior, the 'has_more' flag, and the cap at 100 to 'stay polite.' It also discloses that paging is capped and that spoiler-heavy books can return fewer than limit. This is rich, non-obvious behavioral disclosure.

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 well-structured with a clear opening sentence, a paragraph on backend behavior, and a bullet-like breakdown of parameters. It is slightly longer than strictly necessary, but every sentence adds value—pagination, ordering, aggregation, and parameter semantics are all covered. The front-loading of the core purpose ('actual review text, not just a score') is effective.

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 (5 params, 0% schema coverage, no enums), the description is remarkably complete. It covers what the tool returns, how pagination works, how filters behave, the meaning of 'has_more', and the cap on limit. The output schema exists, so return values don't need to be enumerated. An agent has everything needed to invoke this tool correctly and interpret its results.

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 carries the full burden of explaining parameters. It explains limit (max reviews, capped at 100), min_rating/max_rating (server-side star filters with examples like min_rating=4 for positive reviews), and exclude_spoilers (drop flagged reviews). It also explains the interaction between exclude_spoilers and pagination. This fully compensates for the lack of 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?

The description states a specific verb ('Get') and resource ('reader reviews for a book'), and immediately distinguishes itself from a mere score by noting it returns 'the actual review text, not just a score.' It also clarifies it fetches from Goodreads' GraphQL backend, aggregates across editions, and returns reviews in 'most relevant' order, which clearly differentiates it from siblings like get_book or get_editions.

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 context on when to use this tool: when you need review text, not just a score. It explains pagination behavior, the 'has_more' flag, and the effect of filters like exclude_spoilers. It doesn't explicitly name sibling alternatives or state when not to use it, but the context is strong enough for an agent to select it appropriately.

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/openWorld/non-destructive, and the description adds meaningful context beyond that: no authentication needed, the RSS page size (~100 items) and 1-based pagination, the ValueError failure mode, and the defaulting to the configured GOODREADS_USER_ID.

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 core action, then constraints, pagination, and defaults in short sentences; the closing note about linking the 'link' field is a compact, useful output cue. No 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?

With an output schema present and annotations covering the safety profile, the remaining agent-relevant details — auth, valid inputs, error behavior, pagination, defaults — are all supplied. Nothing needed for correct invocation 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 0%, so the description carries the full burden and does: shelf (case-sensitive, must match a known shelf, empty = all shelves, defaults implied), page (1-based, ~100 items per page), and user_id (defaults to configured GOODREADS_USER_ID). All three parameters gain meaning not present in the bare 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?

States a specific verb and resource ('List books on a shelf') plus the mechanism ('via its RSS feed'), which cleanly separates it from siblings like search_books and get_book.

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?

Gives concrete operating conditions: public shelves need no auth, names are case-sensitive and must match a shelf from list_shelves or ValueError is raised, and an empty name lists all shelves. It points at the list_shelves sibling for valid inputs, though it does not explicitly contrast when to prefer this over search_books.

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 mark the tool as read-only and idempotent, and the description adds valuable behavior beyond that: the data is scraped and best-effort, private profiles raise LoginRequired, and very long shelf lists may be capped. These edge cases are non-obvious and useful.

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 and front-loaded: the core purpose is in the first sentence, followed by short, relevant caveats about scope, failure mode, and limitations. Every sentence adds unique information with no 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 simple optional-parameter read-only tool with an output schema, the description covers purpose, default behavior, shelf scope, relation to get_shelf, failure behavior, and a known limitation. Nothing essential is missing for an agent to 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 only parameter, user_id, has no schema description, so the description carries the burden. It explains the default behavior ('Defaults to the configured user') and implies that supplying user_id targets another profile. It does not spell out the expected user_id format, leaving a minor gap.

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 and resource: 'List a user's shelf names.' It further clarifies scope by distinguishing exclusive shelves from custom shelves and ties the output to get_shelf's 'shelf' argument, making the tool's role distinct from 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?

It provides clear operational context: defaults to the configured user, covers all shelf types, and explicitly connects the result to get_shelf. It does not explicitly state when not to use this tool or name alternatives, 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 readOnly/idempotent/openWorld, so the safety profile is covered. The description adds genuinely useful behavior beyond that: a year/month with no chart raises an error rather than returning empty, and the limit is capped at 50. It does not mention pagination beyond the cap, which is the only gap.

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 purpose, then parameters, then return shape. Slightly redundant in restating the source page URL, and the trailing return-value sentence is partly unnecessary given an output schema exists, but overall efficient.

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 3-param read tool with full annotations and an output schema, the definition covers the key edge case (error on missing chart) and the entry structure. Complete enough to invoke correctly; only the parameter defaults and any alternative-tool guidance are unaddressed.

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 the load, and it largely does: year as 4-digit release year, month as optional 1-12, and limit as capped at 50. It omits the default values (20, null) present in the schema, but otherwise compensates well for the missing 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 a specific verb+resource ('Most popular books by release date') and anchors it to a named Goodreads chart. It is clearly distinct from siblings like search_books or similar_books, which serve different retrieval modes.

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?

Gives clear context ('Mirrors the goodreads.com/book/popular_by_date/<year>[/<month>] page') and states that results can be chained into get_book/get_reviews. However, it never explicitly says when to prefer this over search_books or book_lists, so the alternative-routing is left to inference.

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 mark it read-only and idempotent; the description adds non-obvious implementation behaviors: 'JSON autocomplete endpoint (no auth, no HTML parsing)' and the hard cap of roughly '~5 matches' regardless of max_results. It also lists return fields, giving the agent accurate expectations. No contradiction with 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 compact and front-loaded: purpose first, then implementation/return behavior, then the max_results caveat. Every sentence earns its place and there is no 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 simple two-parameter read-only search, the description covers auth, parsing behavior, return contents, and result cap. The presence of an output schema means return-value details do not need to be repeated, and no invocation-critical information 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 provides no property descriptions, so the description must compensate. It gives query meaning ('by title/author/ISBN') and fully explains max_results, including that larger values do not increase results beyond the endpoint's ~5-match limit. This is sufficient, though query syntax could be more detailed.

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 and resource: 'Search Goodreads for books by title/author/ISBN.' This clearly differentiates it from siblings like get_book (specific book) or author_books (author-scoped) by emphasizing broad 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?

It establishes a clear use case: finding books by title, author, or ISBN. It does not name alternatives or state when not to use it, but the context is sufficient for an agent to select it over more specific sibling tools.

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?

Adds behavioral detail beyond annotations: pagination in batches, limit capped at 100, and semantics of returned fields (placement and is_primary). No contradiction with readOnly/idempotent 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 compact paragraphs, front-loaded with the core action and structured with parameter guidance and output details. No filler or redundant repetition of annotations.

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 description covers purpose, disambiguation, output field semantics, and pagination constraints. With the output schema available and read-only annotations, an agent has everything needed to call 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 has 0% description coverage, but the description explains all three parameters: book_id is the input book in the series, series_index is zero-based and references get_book's series_memberships order, and limit is capped at 100. This fully compensates for the schema gap.

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 the precise verb 'List' with resource 'books in a series' and a distinguishing attribute: reading-order placement. Clearly distinguishes from sibling tools like author_books and similar_books by focusing on a given book's series membership.

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?

Explains when to use it: given any book in a series, list its books; also gives a specific conditional: when a book belongs to multiple series, pass the zero-based series_index from get_book's series_memberships order. Does not explicitly rule out alternatives but provides clear context and a concrete workflow referencing get_book.

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, openWorldHint, idempotentHint, and destructiveHint=false. The description adds useful behavioral details beyond those: results paginate in batches, limit is capped at 100, and each result includes book_id/title/author/rating/url. This is meaningful context without contradicting 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?

Three sentences with no wasted words. The purpose is front-loaded, and the additional details about result fields, chaining, pagination, and limit cap each earn their 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?

For a simple two-parameter read-only tool with an output schema, the description is complete. It covers the data source, result contents, chaining opportunities, pagination, and limit cap. Nothing essential is missing for an agent to 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?

Schema description coverage is 0%, so the description must compensate. It explains the limit cap and pagination behavior, but does not elaborate on book_id semantics beyond 'the given one.' The default limit is already in the schema, so the description adds some but not full parameter clarity.

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 books similar to a given one, using Goodreads' own recommendation graph. This distinguishes it from web search and implies a specific resource and behavior. The 'Readers also enjoyed' framing makes the purpose immediately recognizable.

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 gives clear context for when to use the tool: when Goodreads' recommendation graph is needed, and notes that it is hard to reproduce via web search. It also suggests chaining into get_book or get_reviews, but does not explicitly name alternative sibling tools or when not to use them.

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