Books Like This

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

Annotations only cover the safety profile (readOnly, idempotent, openWorld), and the description adds substantial behavior beyond that: the ranking model (picked_from: shelf vs subjects), the exclusion policy (no self-help, textbooks, anthologies, study guides, category romance lines, or explicit books), the one-per-author/one-per-series rule, preference for popular books, and the same_author override. This is unusually rich 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?

Purpose and examples are front-loaded, and every subsequent sentence carries real rule content rather than filler. The middle run-on sentence covering exclusions and popularity is dense, but trimming it would lose operative 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?

With no output schema, the description partly compensates by explaining the picked_from and because fields and the ordering of results. Behavior is well covered, though the exact response shape (fields, counts, shop links) is only partially inferable, leaving a small 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?

Schema coverage is 100%, so the baseline is 3, but the description adds value beyond the schema by explaining the effect of same_author=true and the semantics of the picked_from/because output tags tied to inputs. It reinforces title/subject usage but adds little new for country.

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 resource (recommended books) and the two trigger cases ('books like The Martian', 'a good cosy mystery'), with concrete examples. It also distinguishes itself from the author-listing sibling by stating that other books by the same author are excluded unless same_author=true, so an agent can tell it apart from get_author_books without opening a 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?

Gives clear invocation context ('Give title or subject') and shows both consumption modes with examples. It does not explicitly name the sibling tools or state when-not to use this tool, but the title-vs-subject routing is explicit enough to steer correct use.

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 and non-destructive, so the safety profile is covered. The only behavioral addition is the "newest first" ordering, which is useful but also just a restatement of the title; nothing about result size, pagination, or edge cases (e.g., ambiguous author names) is disclosed.

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 short sentences, front-loaded with the core behavior, with no filler. It loses a point only because the first sentence duplicates the title verbatim rather than spending those words on new 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 simple two-parameter lookup with no output schema, the description states what is returned (the author's books) and how they are ordered, which is adequate. It omits what a book entry contains and how ambiguous or missing authors are handled, leaving minor gaps.

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 both the author and country parameters are already documented (including the country enum values in the schema) and the baseline of 3 applies. The description adds no syntax, format, or disambiguation detail for parameters beyond what the schema provides.

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?

Names the resource (an author's books) and its ordering (newest first), and the quoted example requests make the intent unmistakable. It never names or contrasts with its siblings (find_similar_books, get_book), so it falls short of the 5-level sibling differentiation.

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?

"For requests like 'what has Andy Weir written?'" gives an implicit trigger for use, which is more than nothing. However, there is no guidance on when to prefer this over get_book or find_similar_books, and no exclusions or prerequisites.

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 cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description's value is in the operational caveats it adds: misspellings are tolerated, and when screen_checked is false the film/TV check did not run and adaptation status is unknown. That graceful-degradation disclosure is meaningful behavioral context 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?

Purpose is front-loaded in the first clause, followed by three short illustrative examples and one caveat sentence; every sentence carries information. It is slightly list-like but not padded, and no sentence is redundant with the 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?

With no output schema, the description must signal what comes back, and it does state that results include book details plus film/series adaptation status, including the screen_checked failure mode. It leaves the exact shape of the response (fields, buy links implied by the country param) unstated, which is a minor residual 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?

Schema description coverage is 100%, so title, author, and country are already documented with guidance (adding author for short/common titles, country for buy links). The description only adds the misspelling tolerance for the title parameter, which is a marginal supplement rather than a gap-filler, so the 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 names the resource (a book's details) and a distinctive secondary capability (any film or series adaptation) that neither sibling, find_similar_books nor get_author_books, offers. The three sample requests make the scope concrete and unambiguous for an agent choosing among the three tools.

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 examples ('tell me about Project Hail Mary', 'is The Name of the Wind being made into a film?', 'how long is Dune?') give clear triggering scenarios, and the note that misspellings are tolerated reduces hesitation to call it. It stops short of naming the sibling tools or stating when this tool should NOT be used instead.

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