project_semantic_diff

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

With no annotations, the description must disclose side effects and behavior fully. It mentions the fallback mode (cached index vs fresh read) and that it compares snapshots, but does not state whether it is read-only, whether it triggers any index refresh, or what kind of output is returned. This leaves significant ambiguity about the tool's operational impact.

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?

Two sentences, no redundant wording. It front-loads the core action and resource scope, then explains a key behavioral branch efficiently. Every clause adds meaningful 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?

Given no output schema and no annotations, the description should explain return values and side effects. It covers the two operating modes and scope, but lacks any indication of output format, result details, or whether the operation modifies state. This is adequate but has clear gaps for a complex comparison tool.

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 parameters are already documented. The description adds a small semantic layer by explaining how omitted snapshots cause a fallback to cached-index-vs-fresh-read, which ties to the before_snapshot/after_snapshot parameters. This interaction adds value beyond the schema descriptions.

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 compares indexed before/after snapshots for semantic changes, specifying resource types (Blueprints, widgets, materials, level actors, dependencies). This distinguishes it from sibling tools like project_index_query or asset_list by focusing on diffing snapshots.

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?

Usage is implied: the tool is for comparing snapshots or falling back to cached vs fresh data. However, it does not explicitly state when to use this tool over alternatives (e.g., project_index_query) or provide exclusions. The conditional behavior is clear but no guidance on choosing between tools is given.

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