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

Annotations already cover safety (readOnlyHint=true, openWorldHint=false), so the lower bar applies. The description adds real value beyond them: the ranking logic (lead score plus cost of the open receptionist job) and the fact that each result includes a suggested cold-call angle, which is non-obvious output content.

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?

A single sentence that front-loads the resource and immediately qualifies it with ranking and inclusion criteria; no filler and nothing wasted.

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?

With no output schema, the description does well to describe the ranking and the returned call angle. But it omits the two parameters and gives no routing guidance relative to its many siblings, leaving gaps an agent must guess at.

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% and neither 'limit' nor 'industry' is mentioned anywhere in the description. With two undocumented parameters, the description leaves the caller to infer that results can be capped or filtered by industry.

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?

Names a specific resource (leads to call) and defines its scope precisely: 'not yet won or lost, with a phone number, ranked by lead score.' That filtering criteria distinguishes it from siblings like find_leads or my_follow_ups, though no sibling is named explicitly.

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?

'Right now' and 'best leads to call' imply a prospecting/cold-calling use case, but the description never states when to prefer this over find_leads, my_follow_ups, or lead_details, nor any prerequisites or exclusions.

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