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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly explains that backfill rows are counted apart, that rows where publication_time_is_ours is true have zero lag by construction, and that the metric reflects collection speed rather than news-market speed. These are substantive edge cases and interpretation caveats, not just restatements of the schema.

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 opening sentence immediately states the core purpose, and later sentences each add meaningful behavioral context. It is somewhat long, but every sentence earns its place with caveats that materially affect interpretation.

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 tool with 6 parameters, no annotations, and no output schema, the description is remarkably complete. It explains the metric units, the grouping by feed, the backfill behavior, the special zero-lag case, and a market-speed caveat, giving an agent everything needed to interpret results correctly.

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 baseline 3 applies. The description adds contextual framing about the 90-day window and per-feed grouping, but it does not elaborate on parameter syntax or formats beyond what the schema already documents.

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 measurement task: how long after a source published a record it reached us, with median, 90th percentile, and worst case in seconds per feed. This clearly distinguishes it from siblings like geo_records or geo_sources, which focus on records or source metadata.

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 its use case from the task definition, and it gives useful context about backfill counting and the publication_time_is_ours caveat. However, it never explicitly names alternative tools or explains when not to use it, leaving the routing to inference rather than clear guidance.

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