topic_trend

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

With no annotations, the description carries the load and does well: it discloses matching behavior (whole-word, trailing * for prefix), the returned structure (per-term summary plus one row per period), and the normalization per 1,000 stories that makes periods comparable. It omits operational details like default time range when since/until are null and how granularity affects bucketing.

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?

Front-loaded with the core definition, then return shape, then a use case — every line is relevant. Slight verbosity in the return-shape sentence ('compact table: one row per period...') but 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?

The absence of an output schema is offset by a solid description of the return format, and the absence of annotations is partly offset by disclosed matching behavior. However, the missing time-range and granularity semantics leave an agent unable to call it precisely for anything but the default case.

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 0%, so the description must compensate. It adds real meaning for `terms` (whole-word vs prefix matching, example values) but says nothing about `since`, `until` (both untyped strings — format unknown), or `granularity` (the year/month enum and its effect on row bucketing), leaving three of four parameters undocumented.

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?

States a specific computation over a specific resource: per-term occurrence counts within story titles over time, with explicit matching semantics. It is clearly distinct from retrieval siblings like search_stories and get_thread because it returns aggregates rather than stories, though no sibling is named directly.

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 only implied via 'Good for "rise and fall" charts' with an example query. There is no explicit statement of when to prefer this over search_stories or run_sql, and no exclusions or prerequisites.

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