index

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

With no annotations provided, the description carries the full behavioral burden. It discloses that the tool writes to a durable SQLite substrate at .scplus/state/index.sqlite, persists various artifacts (project config, stage state, indexing status, caches, restore points, indexes), and that full mode persists additional artifacts. It also notes 'no JSON mirrors,' a specific behavioral trait. This goes beyond simple 'indexes the repo' and gives a clear picture of side effects.

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 a single, dense, run-on sentence that combines many details. While every clause adds relevant information, it lacks clear structural breaks (e.g., separate sentences or bullets) that would improve readability. It is not overly long, but the phrasing 'and in full mode also persists...' could be better organized.

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 the tool's complexity (multiple artifacts, modes, persistence details) and the absence of an output schema and annotations, the description provides a thorough account of what happens and where. It explains the two modes, storage location, and what is persisted. However, it does not mention return values or error conditions, but for an indexing tool this is a minor gap.

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 input schema has full coverage (100%) with mode's enum and description, so baseline is 3. The description adds significant value by explaining that mode defaults to full and that full mode persists chunk and code-structure artifacts with contract metadata. This clarifies the practical difference between core and full beyond the schema's simple enum.

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 the tool's function: 'Create or refresh the .scplus project state for this repo.' It specifies a concrete action (create/refresh), a specific resource (.scplus project state), and the scope (repo-local). This distinguishes it from sibling tools like status, validate_index, and repair_index, which operate on or query existing state rather than building 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?

The description implies usage: run this to (re)build or refresh project state, but it does not explicitly state when to use this vs. alternatives. It does not mention that status, validate_index, or repair_index are for checking or fixing an existing index, nor does it provide when-not-to-use guidance. Thus, usage context is present but relies on inference.

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