bookshelf_storage

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It does flag some operations as WRITE (bookshelf_create_rootfolder, bookshelf_update_rootfolder) and DESTRUCTIVE (bookshelf_delete_rootfolder), which is helpful. However, it does not explicitly state that the list/get operations are read-only, nor mention any side effects, permissions, or rate limits. The description adds some transparency but leaves gaps, especially for a tool that modifies data without 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 structured as a bulleted list of sub-operations, each with a concise one-liner and occasional notes (WRITE, DESTRUCTIVE, query params). It is front-loaded with the general instruction to pass operation and arguments, then delivers the list. There is minimal fluff and each line serves a purpose. It is not overly verbose, though it could be tightened by grouping, but overall it is readable and 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?

The tool is complex (dispatcher for 9 sub-operations) and has an output schema, so the description need not explain returns, but it must be complete enough for operation selection and parameter construction. While it lists all operations and some parameters, it omits detailed parameter schemas (e.g., what body should contain for create/update, what the path format is). This is a significant gap for an AI agent, as it would need to infer these details. The description is adequate for identifying the operation names but not for actually invoking them with proper arguments.

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 lists parameter names for each sub-operation (e.g., body, id, path, include_files), but does not explain their meaning, types, or formats beyond what is in the enum. For instance, body={} and id are mentioned without describing required fields or constraints. The description only gives a brief hint like 'Query params: path, includeFiles, allowFoldersWithoutTrailingSlashes' but does not define these parameters. This is insufficient for an agent to construct correct arguments without additional knowledge.

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 that the tool performs bookshelf storage operations and lists specific sub-operations like create/delete/update rootfolders and listing operations. It uses specific verbs (create, delete, update, list, fetch) and resources (rootfolder, filesystem, diskspace), which distinguishes it from the sibling tools that focus on other domains (e.g., media library, indexers). However, it is a dispatcher tool rather than a single action, so the purpose is clear but not as focused as a single-purpose tool.

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 no explicit guidance on when to choose this tool over its siblings such as bookshelf_media_library or bookshelf_config. It implies that it is for storage operations, but there is no mention of alternatives or exclusions. The only contextual hint is the list of sub-operations, which suggests a storage-related use case, but without explicit 'use this when' or 'don't use for' instructions, the agent must infer the scope.

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