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

Annotations already cover read-only and open-world, yet the description adds genuine behavior: no account or API key required, per-source graceful degradation with the failed source named in the reply, and how Open Library results are classified as 'free' vs 'borrow'. Only the result ordering/merging across sources is left unstated, so this is useful added context rather than a contradiction.

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 and sources, then inputs, then fallback behavior, then an example. Mostly earns its space, though the 'Inputs:' sentence duplicates schema content that the agent already receives.

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 and annotations present, the description covers what the agent needs: sources searched, input flexibility, auth requirements, and partial-outage behavior. Only result ordering/deduplication across the three sources is left to the output schema or inference.

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 baseline is 3, but the description adds a detail the schema omits: the limit applies 'from each source' rather than overall, which changes how an agent sets it. The query guidance (title, ISBN, or course topic) largely restates the schema but confirms the accepted input forms.

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?

Specific verb plus resource: 'Search for free and legal copies of a textbook' across three named sources (OpenStax, DOAB, Open Library). It is clearly separable from siblings like lookup_isbn and list_open_textbooks_by_subject because it is a cross-source search rather than a single-record lookup or subject browse.

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 example prompt ('Is there a free legal copy of the Calculus textbook by Stewart…') implies the intended use case, and the query description ('a book title, an ISBN or a course topic') implicitly advertises the broad input space. However, no sibling is named, so an agent gets no guidance on when to prefer lookup_isbn (which overlaps with the ISBN query form) or list_open_textbooks_by_subject, and there are no when-not conditions.

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 annotations already establish that this is a read-only, open-world lookup. The description adds useful behavioral context: it does not know prices, suggestions are ordered from the closest older edition downward, and results should be checked against the syllabus.

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 purpose and generally well organized. It is slightly verbose for a three-parameter tool because it repeats schema details such as the 1-to-10 limit and includes a full example prompt.

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 simple parameter set, complete schema descriptions, annotations, and an output schema, the description covers the important usage context and limitations. An agent has enough information to call the tool correctly and interpret the caveat about edition contents.

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 complete, so the baseline is 3. The description adds meaning beyond the schema by explaining that query can be a title or ISBN, that edition_year represents the course-required edition year, and that omitting it treats the newest listed edition as current.

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: suggesting earlier editions of a textbook. It is clear what the tool does, but it does not explicitly distinguish itself from sibling tools such as find_free_textbook or lookup_isbn.

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 example prompt and the course-edition scenario make the intended use case clear. However, it does not explicitly say when to use this instead of the sibling tools or 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?

Beyond the readOnly/openWorld annotations, the description discloses result ordering (OpenStax first) and graceful degradation when DOAB is unavailable, including that the response signals the partial result. That is meaningful operational context not present in structured fields, though rate limits or result-shape details are absent.

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 four short sentences and front-loads what the tool returns before covering inputs and failure behavior. The trailing example prompt is slightly redundant but does usefully illustrate the intended subject 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?

An output schema exists, so return-value structure need not be explained. The description still covers the multi-source merge, ordering, and the DOAB-outage case, which is what an agent needs to set expectations; only sibling routing is left 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 coverage is 100%, so both the subject examples and the 1-to-25 limit range are already documented in the input schema. The description restates them rather than adding new semantics, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a specific verb and resource ('Browse free textbooks for a course topic') and names the two sources it aggregates, OpenStax and DOAB. It does not explicitly contrast itself with siblings like find_free_textbook, but the browse-by-subject scope is distinct enough that an agent can infer the difference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied through the example prompt ('List free textbooks for intro statistics'), which suggests a broad topical query. There is no explicit statement of when to prefer this over find_free_textbook or find_older_edition, and no exclusions or prerequisites are given.

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, so the description goes further by disclosing that the check digit is validated before any search, which explains error behavior, and that related editions come back newest first. That ordering and validation detail is genuinely useful context not present in 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 front-loaded with the core action and stays compact. The sentence enumerating return fields (title, authors, publisher, publish date, page count, edition name) is somewhat redundant given the output schema, but it is brief and helps set expectations.

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 has one required, fully documented parameter, read-only annotations, and an output schema, so the description only needs to establish purpose, validation behavior, and result ordering, all of which it covers. There are no material gaps for an agent calling a single-parameter lookup.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema itself documents the ISBN format, hyphens and spaces included, so the description's restatement of '10 or 13 digits, hyphens allowed' adds no new meaning. The one extra is the note that the check digit is validated first, which hints at the failure mode but gives no format for the error.

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 and resource ('Look up an ISBN on Open Library') and names the scope of the result (edition details plus other editions of the same book). It does not explicitly distinguish itself from related siblings such as find_older_edition or find_free_textbook, whose functions the described output partly overlaps with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an example prompt shows a lookup in context, but there is no statement of when to prefer this tool over find_older_edition or find_free_textbook, or of any preconditions. The agent must infer the routing from the example alone.

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