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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true. The description adds valuable context beyond these: partial success is normal (failure semantics) and writes land in a shared workspace with no per-caller isolation (side-effect and concurrency implications). This is exactly the kind of behavioral disclosure that helps an agent predict outcomes.

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?

Three sentences with no filler. The main action is stated first, followed by failure behavior and workspace implications. Every sentence adds information, and the description is appropriately short for the tool's simplicity.

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 the tool has no input schema, the description must explain how to invoke it. It mentions Apollo IDs but not the request body structure, the set of updatable fields, or how partial success is reported. The output schema exists but is not described, so the agent still lacks guidance on what to pass and what to expect. For a bulk mutation tool, this is incomplete.

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?

The schema has zero parameters, so the description carries the entire burden. It mentions 'each identified by its Apollo id,' which indicates that the input must include Apollo IDs, but it does not specify the structure (e.g., a list of objects, how to pass them, or what fields are updatable). For a tool with no schema parameters, this is only a partial hint and leaves the agent guessing about the exact request format.

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 clearly states the action: 'Update several contacts in one call, each identified by its Apollo id.' It names the resource (contacts), the verb (update), and the bulk scope, which distinguishes it from single-contact patch tools and bulk-create tools. It effectively differentiates itself without needing to name siblings.

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 description does not explicitly say when to use this tool instead of alternatives, such as patching contacts individually or using bulk create. It only implies bulk updates, but provides no exclusions or conditions like 'use this when updating more than one contact' or 'not for single updates.' This is a significant gap for an agent deciding between many sibling tools.

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