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

Annotations only declare readOnlyHint=true; the description adds a real workflow precondition about not submitting facts before the engagement begins, which is context the annotation cannot carry. It doesn't describe what the returned schema looks like or whether narrowing alters its shape, so it is useful but not complete.

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 short sentences: identity of the resource first, optional narrowing second, the precondition last. No filler and nothing buried.

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 two-optional-enum read tool with no output schema, the description covers purpose, narrowing behavior, and a key precondition, and it names the output format as a JSON Schema. Only the default (un-narrowed) result and the schema's shape remain unstated.

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?

With 50% schema coverage, the description compensates by explaining the effect of both parameters – that governing law and role optionally narrow the result set – which the schema's enum lists alone do not convey. It still doesn't clarify the default behavior when both are omitted.

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?

States a specific verb+resource ('the facts the data processing agreement needs') and the return type ('as a JSON Schema'), which distinguishes it from the submit_* siblings that instead send those facts. An agent can tell it apart from get_requirements and submit_dpa_facts without opening a 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?

Explains the optional narrowing by governing law and role, and adds an ordering constraint ('Do not send the facts until the engagement has begun') that implies a separate submission step. It stops short of naming submit_dpa_facts as the alternative, so the sibling routing is only implied.

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