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

With no annotations, the description carries the full behavioral burden. It usefully discloses "Safe, no cost", which tells the agent this is a non-billing operation. However, it omits that this is a mutation that overwrites stored weights, whether it is idempotent, whether a minimum volume of outcome data is required, and what permissions are needed.

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 tight sentences with the operation and its data source front-loaded, followed by the safety profile and trigger condition. No filler and nothing buried.

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 one-parameter mutation tool with no annotations and no output schema, the description covers what it does and its risk profile, but leaves open whether prior weights are replaced, what preconditions exist, and what the caller gets back. Adequate but with visible gaps.

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% for the single search_id parameter, so the description must compensate. "For one search" implies the parameter identifies the target search, but it adds no format, source, or lookup guidance (e.g., from sdr_list_searches), leaving the parameter largely undocumented in both places.

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 names a specific verb (recalculate) and a precise resource (per-signal-type weights derived from replies/meetings vs sends) scoped to one search, so an agent can distinguish it from sdr_learning_insights and sdr_signal_stats. It stops short of explicitly naming which sibling to use instead when the user only wants to view weights, so it is clear but not fully differentiated.

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?

"Use when the user asks to refresh/recalculate Signal Learning" gives an explicit trigger condition, and "Safe, no cost" signals it is low-risk to invoke. There is no when-not guidance (e.g., do not call if no outcomes exist yet) and no named alternative, so it is clear context without exclusions.

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