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

Annotations already declare readOnlyHint=false and idempotentHint=false, yet the description adds real substance: the POST /leads endpoint, the assignment dependency that gates step, and the parsing contract that the server reads the free-text description line by line. These are non-obvious side effects and preconditions not derivable from the annotations.

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?

Four short clauses, front-loaded with the write semantics, then the description format, then the assignment rule, then the idempotency warning. No filler and nothing buried at the end that changes the decision to call.

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 5-parameter creation tool with rich annotations, the description covers the mutation, the parsing format, and the assignment precondition. The remaining gap is the return value — with no output schema, nothing states whether the new lead's id comes back, which an agent needs to chain into follow-up calls.

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 baseline is 3, but the description earns above that by explaining the cross-parameter dependency (step requires user_id; no user_id means unassigned) and by specifying the 'Label: value' line syntax for description. It doesn't touch tags or title beyond what the schema states.

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?

Opens with an explicit verb+resource ('WRITE: create a new lead') and a typed prefix that separates it from read siblings like nocrm_get_lead and from the mutation sibling nocrm_update_lead. An agent can route on this line alone without opening the 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 concrete usage conditions: omit user_id to create unassigned, and step is only valid when the lead is assigned. It also warns 'calling twice creates two leads', which signals a dedupe check before calling. It never names an alternative tool (e.g. nocrm_update_lead for existing leads, nocrm_get_lead_duplicates for pre-checks), so it stops short of full when/when-not routing.

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