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

With no annotations, the description carries the full burden and does well: it discloses acceptance preconditions, that a package containing a name/e-mail/postal address held for the matter is refused, that counterpartyLegalName must be omitted because the firm supplies it, and an extra BAA/PHI restriction. It stops short of describing what a successful submission returns or how refusals are surfaced, which matters since there is no output schema.

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?

Content is front-loaded as a single dense paragraph: identity and shape first, then acceptance rules, then content restrictions. The prohibition on names/e-mails/addresses is restated for both "do not send" and "will be refused," which is mild redundancy but each clause adds a distinct nuance (interaction vs. validation).

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 4-required-parameter mutation with a nested open-ended object, no annotations and no output schema, the description covers preconditions, content rules, exclusions and refusal behavior. The remaining gap is the response/error contract, which nothing else in the structured data supplies.

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 the enum and id/token parameters are already documented; the description's added value is on the free-form nested `facts` object, where it prescribes substitute wording ("the Client", "the Customer"/"the Vendor") and exclusions. That meaningfully constrains the one parameter the schema leaves as additionalProperties, exceeding the baseline 3.

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 identifies the resource ("the fact package for the matter's service") and its schema id, but never states a verb — the action is only carried by the name and title. It also does not distinguish itself from the sibling submit_dpa_facts, leaving the agent to infer which submission tool applies to a given service.

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?

Timing/preconditions are explicit: "Accepted only once the engagement has begun, and again when the lawyer asks for changes," and it points to get_requirements for the shape. It gives clear when-to-call context, but names no alternative when this tool is not the right one (e.g. submit_dpa_facts or open_matter ordering).

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