stl_diff_summary

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

Annotations already cover read-only, idempotent, and non-destructive behavior, and the description does not contradict them. It adds useful behavioral context by explaining that findings are graded and that direction matters, giving the user a clearer expectation of the tool's output and sensitivity to argument order.

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 concise but includes a slightly stylistic explanatory sentence about why findings are graded. That sentence is informative rather than redundant, and the overall structure is clean: purpose, rationale, and parameter guidance.

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 that an output schema exists, the description adequately covers the tool's purpose and parameters. It explains the input semantics and directionality, and it sets expectations for the summary output. It could mention error conditions or snapshot existence expectations, but these are not critical for basic usage.

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?

Although the schema has 0% description coverage, the text provides meaningful parameter descriptions: 'a' is the earlier snapshot id or pin name, 'b' is the later one, and direction matters. This compensates for the missing schema annotations, though it could be more explicit about allowable formats for snapshot IDs or pins.

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 purpose: 'Everything that changed between two GTFS snapshots, in one screen.' This is specific and distinguishes it from narrower siblings like stl_diff_stop_ids, which focuses only on stop ID changes.

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 for getting a broad, graded summary of changes between two snapshots, but it does not explicitly mention when to prefer this over alternative diff or snapshot tools. It does provide practical guidance that direction matters and is not normalized, which helps avoid misuse.

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