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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false). It discloses the dedup rules (same published email/phone, or business name + phone), what the preview returns (counts of new/duplicate/missing-contact rows, chosen pipeline and stage, first 5 rows), and resumability semantics (finished rows skipped, half-done rows completed, never duplicated). No contradiction with idempotentHint=false, since a re-run after partial failure does produce additional effect by completing half-done rows.

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?

Dense but front-loaded: the core action, the dedup behavior, and the preview/confirm flow come first, with prerequisites and the sibling comparison last. Every clause carries information, though the single long paragraph is heavier than it needs to be and could be split for scanability.

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?

There is no output schema, so the description carries the return-value burden itself: it describes the preview payload (counts, pipeline/stage, first 5 rows) and the confirm-mode effect. Combined with the write annotations and 100%-covered schema, an agent has everything needed to call this correctly, including error-adjacent cases (writes disabled, partial failure).

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 the baseline is 3, but the description adds meaning beyond the schema by framing parameters in the workflow: the preview resolves and reports the pipeline/stage (first pipeline's first stage unless chosen, all pipelines listed when more than one) and confirm is tied to explicit user agreement. It also clarifies the dedup key used by ids/run_id selection. It stops short of explaining edge cases like the 60-id or 10-tag caps.

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?

Specific verb+resource: it pushes a whole find_prospects run into the agency's HighLevel sub-account in one call, and it enumerates exactly what is created (contact fields, a note, an opportunity in a pipeline stage). It explicitly distinguishes itself from the sibling highlevel_create_prospect ("Use this instead of highlevel_create_prospect per prospect"), so an agent can choose between them without opening a schema.

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?

Gives explicit when/when-not guidance: call without confirm first to get a preview, and set confirm only after the user agrees to that exact change. It names the per-prospect alternative, states the prerequisite (CRM writes must be on, and the preview reports when they are off), and reassures that nothing is sent to anyone.

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