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

Beyond the annotations, the description discloses important behavioral traits: this invokes a shared backend action, should not be followed by a state-recovery call, has idempotency obligations, and does not require additional confirmation. These details meaningfully help an agent predict side effects and post-call behavior, beyond what readOnlyHint/destructiveHint provide.

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?

The core action is front-loaded and the description is organized into scannable labeled sections like Prerequisite, Canonicality, Idempotency, and Confirmation boundary. Some phrases are boilerplate or vague ('plus every prerequisite stated above'), adding minor noise, but the overall structure remains efficient.

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 complex 10-parameter mutation with no output schema, the description covers the key operational context: subject identity, where to record facts, prerequisite auth, output trust, idempotency, and confirmation. It leaves detailed parameter semantics to the schema and does not fully explain plan-resolution mechanics, but it is sufficiently complete for correct invocation.

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?

Input schema coverage is 70%, and the schema already documents companyId, externalKey, linkedUserId, attributes, itemLimit, and questionLimit. The description adds useful guidance about stable externalKey and that attributes must not hold decision facts, but it does not compensate for the remaining undocumented parameters. This is adequate but not exceptional.

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 opens with a specific verb-resource pair: 'Create or update one durable company-owned subject', and enumerates ten subject types, making the tool's scope immediately clear. It also differentiates itself from record_operating_fact by explicitly routing decision facts to that sibling, so an agent can distinguish it from nearby tools.

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?

It gives explicit routing guidance: 'Use a stable externalKey' and 'store decision facts through record_operating_fact, not opaque attributes.' It also provides prerequisites and idempotency/confirmation guidance. However, it does not explicitly state when not to use this tool in favor of other operating tools, leaving some inference to the agent.

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