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

With no annotations provided, the description carries full behavioral disclosure burden. It conveys the core preview trait — nothing actually runs — and flags cost implications of certain sources. However, it leaves ambiguity about whether the preview itself consumes credits and what its output is, which matters for a cost-sensitive tool.

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 sentences with no filler: the first states the purpose, the second explains the cost-driven motivation. The paid-source examples are compact yet informative, and the purpose is front-loaded.

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 preview tool with no output schema and no annotations, the description should disclose what the preview returns (estimated count, credits, matched data?) — it doesn't. It also never explicitly contrasts with sdr_run_now to tell the agent when to prefer the real execution. The cost motivation is well covered, but the return-value gap and missing sibling differentiation leave it incomplete.

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 50%; the source parameter is documented in the schema while search_id has no description. The description adds semantic value by naming which source values are costly to run, helping the agent reason about source choices. It doesn't compensate for the undocumented search_id, but search_id's purpose is largely inferable from the tool's domain.

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?

Uses a specific verb-resource pair ('Show what would happen if you trigger an immediate hunter run') that clearly conveys this is a dry-run. The title reinforces the preview nature, distinguishing it from the sibling sdr_run_now, though it doesn't explicitly name the sibling.

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?

Provides a concrete when-to-use rationale: sources like ai_web_hunter, g2_reviews, and tech_stack are paid, so previewing before running is valuable. This gives the agent clear context for selecting this tool over the actual run tool, though it stops short of explicitly stating 'use sdr_run_now when you intend to execute'.

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