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

With no annotations provided, the description carries the full burden of behavioral disclosure. It tells the agent the aggregation window and that output is counts by source over time, but it does not explain what 'signals' means, whether the data is per-day or cumulative, whether search_id is required and its role, or how results are ordered/paginated. This is partially informative but leaves key behavioral gaps.

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?

One short, front-loaded sentence that conveys the core purpose and the key parameter constraint. Every word earns its place, and the max/default values are included without clutter.

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 simple stats endpoint with 2 parameters, no output schema, and no annotations, the description is adequate but thin. It covers the windowing parameter and the general output shape, but it does not define 'signals', what a 'source' is, how the output is grouped over time, or whether additional filters exist. Given the sibling set has many SDR analytics tools, this could confuse an agent without more context.

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 description coverage is 0%, so the description must compensate for the two parameters. It directly explains days_back ('last N days, max 90, default 30') and implies search_id is the signal source filter context ('Signals collected by source'). However, it does not state that search_id is required, nor clarify what 'source' means in relation to the search. Still, for 2 params it adds meaningful meaning beyond the raw schema.

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 'Signals collected by source over the last N days' clearly identifies what the tool does: it returns signal counts grouped by source within a time window. The verb is implied (stats/list counts) and the resource is specific. Among the large sibling set, it is reasonably distinguishable from sdr_recent_signals and sdr_activity_feed, though it doesn't explicitly call out the differentiation.

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 the primary use case: querying signal volume by source for a search over a configurable trailing window. It states the max/default values for days_back but does not mention when to prefer sibling tools like sdr_recent_signals, sdr_company_heat, or sdr_learning_insights, nor does it give exclusion guidance.

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