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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-obvious semantics beyond that: tags replaces the entire tag list, description text is append-only and never overwritten, and only supplied fields mutate. It stops short of stating irreversibility of status changes or any side effects of moving to won/lost.

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?

Front-loaded with the WRITE label and the object being mutated, then the field list, then the caveats. It is dense but each clause carries information; the enumeration of status enum values and the field list duplicate schema content, which is the only waste.

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 13-parameter mutation with no output schema, the description covers the mutation model (partial update), the destructive replace semantics for tags, the append-only semantics for description, and the conditional remind_date requirement. With annotations carrying the safety profile, nothing an agent needs in order to invoke it correctly is missing.

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 85%, so the schema already documents step, tags, amount, status, remind_date, remind_time, append_description and estimated_closing_date. The description's field list largely restates that content (including the status enum values and the standby/remind_date dependency), with only the partial-update rule adding meaning not already in the schema.

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 classification ("WRITE: change a lead") and enumerates exactly which attributes are mutable, ending with the underlying endpoint PUT /leads/{id}. An agent can immediately distinguish this from nocrm_create_lead or nocrm_assign_lead 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 clear operating conditions: "Only the fields you pass change" establishes PATCH-like partial-update behavior, and "Moving to standby needs remind_date" states a conditional prerequisite. It does not, however, route the agent to siblings for adjacent tasks (assignment, comments, tags listing), so there is no explicit when-not guidance.

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