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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: marking a lead "not_relevant" feeds EvenLeads' learning, and a lead can be returned "back to new", signalling the change is effectively reversible. It still does not say what happens to a lead's other fields or what errors occur for an invalid id.

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: the first front-loads the action and all four accepted values with their meanings, the second states the scope of the write. Nothing is repeated from the annotations or the schema, 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?

For a two-parameter mutation with an output schema (so return values need no explanation) and full annotation coverage of the safety profile, the description supplies the remaining essentials: the valid target states, their meanings, the account scoping, and the learning side effect. Only minor operational details, such as behavior on an unknown lead_id or whether other lead fields change, are left out.

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%: lead_id is documented in the schema, and the status enum values are listed but unlabeled there. The description compensates for the status side by explaining the business meaning of each enum member, which the raw enum strings do not convey. It says nothing about the lead_id parameter and its required integer form, so overall it lands at the baseline-plus level rather than a 4 or 5.

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 gives a specific verb and resource ("Mark one of the user's leads as...") and enumerates the four allowed target states, so an agent immediately knows this is a status-transition tool rather than a read or create tool. It does not name any sibling tool or contrast itself with them, which keeps it just short of a 5.

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?

Usage guidance is present but only at the parameter-value level: "contacted (they sent a message)", "not_relevant (not a fit...)", "closed", "back to new" tell the agent which status fits which real-world situation. There is no tool-level when-to-use/when-not guidance, no mention of prerequisites such as the lead first existing in the account, and no alternatives are referenced.

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