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

Annotations already declare destructive=true, idempotent=true and openWorld=true, so the safety profile is covered. The description adds genuinely non-structured behavior: sparse/partial update semantics and that it returns the policyID. It does not discuss permissions, irreversibility of overwritten values, or failure modes.

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?

One dense sentence, front-loaded with the WRITE marker, then scope, then partial-update semantics and the return value. Nothing is wasted or repeated.

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?

Given a 15-param destructive mutation with a nested custom_fields object and no output schema, the definition is only just adequate: it covers mutation semantics and the return value, but leaves value domains for status/coverage_type/pay_frequency and clearing-behavior of fields unexplained.

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 60% with 15 parameters, so the description only echoes a handful (status, carrier, dates, premium) already present in the schema. Free-text fields like status, coverage_type, and servicing_agent_id get no value guidance in either place, and custom_fields conventions live only 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?

Specific verb (WRITE/change) plus resource (existing policy) with concrete field examples and the underlying endpoint. It is clearly distinguishable from sibling agencybloc_create_policy and agencybloc_update_group/individual.

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?

The phrase 'fields you leave out are not sent' clearly frames this as a partial update, which tells the agent how to invoke it correctly. It stops short of naming alternatives (e.g., use get_policy first to read current values) or stating when not to use it.

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