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

With no annotations, the description carries the full burden and does well: it discloses background/asynchronous execution, idempotency, region/city filtering, and a concrete cost of 5 credits per contact. It stops short of stating failure modes or whether duplicates are skipped vs re-billed on repeat runs, which matters for an idempotent-but-billed 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?

Three tight sentences: what it does, when to prefer the alternative, and the billing consequence. Scope is front-loaded and no sentence is 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?

No output schema exists, and the description covers timing, idempotency, filtering, cost, and the alternative path. Missing only a hint of what is returned (e.g., how many contacts were materialized) and any permission or precondition requirement for a billed mutation.

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 implies job_id refers to a 'finished research' and search_id to the target search whose regions/cities drive filtering, which is genuine added meaning. However, it never names the parameters or notes that a research must be finished before job_id is valid, leaving the UUID formats and validity preconditions to inference.

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 verb ('copies') and precise resource ('instant audience of a finished research into a search as contacts'), and the parenthetical narrows scope to the search's regions/cities. An agent can distinguish this from sdr_create_search and sdr_export_personas_to_audience without opening any 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?

Explicitly names the alternative ('sdr_create_search with research_job_id already does this after activation') and the condition that selects this tool ('use this only to repeat it'). When-to-use and when-not-to-use are both stated outright.

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