Manage content search index

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

Beyond the annotations it discloses substantial behavior: content types indexed, two-at-a-time processing, secret-looking filename skipping, the PROTON_DRIVE_READ_MAX_BYTES size cap, incremental re-read of changed files only, and that 'clear' deletes the index file and keychain key. It also states the crucial scope fact that nothing on Drive is changed and only one local file is written, which the readOnlyHint=false annotation alone would not clarify.

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?

It is front-loaded with the core identity before action details, and nearly every clause carries operational weight. It is a very dense run-on sentence, so a single structural break would improve scanability, but there is little redundant wording.

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 compensates by explaining that 'status' reports counts, size, folders and key backend, and it mentions the partial-result flag. It does not fully specify the shape of 'update' results (e.g., what a partial response looks like), leaving a modest gap for a tool an agent must drive iteratively.

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 real meaning: 'path' never defaults to the whole drive, action 'update' is the default, and indexing skips files over the read-max threshold. Minor mismatch: 'partial' is referenced in the description but is not a declared input parameter, which leaves a small interpretive gap.

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 a specific object (an encrypted local full-text index of file CONTENT), the three concrete actions (update/status/clear), and its opt-in nature. An agent can distinguish this from search-oriented siblings like drive_search_content because it clearly builds/maintains the index rather than querying it.

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?

It gives clear when-to-use context: opt-in flag, action defaults to 'update', and 'if partial:true, call again to continue' tells the agent how to resume. It does not explicitly route to or exclude sibling tools such as drive_refresh_index or drive_search_content, which is the only missing piece for a 5.

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