everything_maintain

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

With no annotations, the description carries the full burden and does disclose real behavioral traits: save_db persists in-memory state, rescan_folders acts immediately on network shares, and rebuild is slow and only warranted on stale results. It does not say whether rebuild discards the current index, whether save_db writes to disk, or whether these operations block, which matters for a maintenance tool with zero annotation coverage.

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?

Telegraphic and front-loaded: a two-word purpose statement followed by colon-delimited definitions of each action, with the cost caveat placed directly on the expensive option. Every clause carries information.

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 one-parameter, no-output-schema tool with no annotations, the description covers all actions and their tradeoffs adequately. The remaining gap is the unaddressed relationship to everything_semantic_reindex, which an agent could easily confuse with rebuild.

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 0%, so the description must compensate, and it does: all three enum values are defined with their operational meaning rather than left as bare tokens. It adds no syntax detail beyond that, but for a single enum parameter the mapping is complete.

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 resource (the file index) and enumerates the three maintenance operations with their distinct effects, so an agent knows exactly what class of action this is. It does not, however, differentiate itself from the sibling everything_semantic_reindex, leaving overlap ambiguous.

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?

Each enum value gets a when-to-use cue: save_db for fast restart, rescan_folders for network shares, rebuild only when results look stale, with an explicit slow warning attached to rebuild. What is missing is guidance relative to alternatives, notably when to prefer rebuild over the sibling semantic_reindex.

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