index_update

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

The description discloses key behaviors beyond the bare annotations: it re-indexes changed files, marks affected claims stale, and returns mode plus affected data. It also reveals the noop/incremental/full mode spectrum, which helps an agent anticipate that calls may be no-ops or expensive full scans.

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 dense sentence that front-loads the core action and scope, then adds the fallback behavior and return values in a parenthetical. Every clause earns its place with no filler.

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 there is no output schema, the description wisely specifies the return shape (mode, changed files, stale claims) and even enumerates the mode values. It could go further on snapshot mechanics or side effects, but for selection and invocation this is largely complete.

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?

The tool has zero parameters, so there is nothing for the description to explain at the parameter level. The baseline of 4 applies because the description sensibly focuses on behavior and outputs instead of nonexistent inputs.

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 ('Re-index'), a precise resource ('files changed since the last snapshot'), and the associated effect ('mark claims whose files changed as stale'). It also names the full-scan fallback, making the tool's role unmistakable against its query/inspect/analyze siblings.

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?

Clear context is provided: this tool is for refreshing the index after file changes, and it falls back to a full scan when no snapshot exists. It does not explicitly name alternatives or exclusions, but the trigger condition and mode behavior make when-to-use reasonably evident.

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