recognize_bookshelf

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

Annotations already declare this is a non-readonly, non-idempotent, open-world operation. The description adds a genuinely useful behavioral detail not in the annotations: it consumes daily credits or BYOK per invocation. It still doesn't disclose that a new collection object is created or what happens on repeated calls.

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?

A single front-loaded sentence packs purpose, the merge-into-collection behavior, and the credit cost with no filler. The parenthetical cost note is slightly compressed but does not dilute the core statement.

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 mutation tool with no output schema, the description does not explain the return (list of recognized books, new collection id, partial-failure behavior). Annotations cover safety and the schema covers inputs, but the post-invocation outcome an agent should expect is left unstated.

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 each parameter richly (mutual exclusivity of image_url/image_base64, the 4-photo limit with a user key, cover_index default). The description adds no parameter detail beyond that, so the baseline of 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 description states a specific verb and resource ('Recognize books from one or more photos of a bookshelf') and adds the key outcome that multiple photos merge into one collection, which separates it from sibling read tools like search_books and get_collection.

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: it tells the agent this is the tool for reading books off photos and that several photos collapse into one collection. There is no explicit when-to-use vs. when-not guidance and no routing toward alternatives, though the input modality (photos) narrows selection enough to make the tool inferable.

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