Find duplicates

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

The description aligns with annotations (readOnlyHint=true) by declaring 'Read-only — never merges'. It adds behavioral details beyond annotations: modes, merge-safety score, field-by-field comparison. This fully informs the agent of the tool's non-destructive nature and output characteristics.

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: the first concisely covers all modes and subset options, the second reinforces read-only nature. Every word is informative, no redundancy. It is well front-loaded with 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?

Given 7 parameters, 3 modes, and existing annotations/output schema, the description covers core behavior and mode distinctions. However, it lacks details on limit (pagination), cursor (continuation), and library parameter. These gaps reduce completeness for an agent expecting full parameter context.

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?

With 0% schema description coverage, the description compensates by explaining mode (enum values), ids/query/filter (subset selection), and clarifying 'filter takes a bundle name'. However, it omits details for limit, cursor, and library, which are unexplained. The addition is adequate but not thorough given the param count.

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 'Find' and the resource 'probable duplicate books', and distinguishes three modes (identical, similar, compare) with specific actions. It differentiates from sibling tools like calibre_search by focusing on duplicate detection, and explicitly notes it is read-only.

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 explains when to use each mode (exact matching, fuzzy grouping, field-by-field comparison) and states the tool never merges, implying it is for identification only. However, it does not explicitly mention alternatives like calibre_search for non-duplicate queries, though the context of siblings makes this implicit.

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