direct.get_changes

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

No annotations are provided, so the description carries the full behavioral burden and falls short. It does not disclose whether this is a read-only polling operation, whether changes are paginated, what the window limit is, or what the response contains, all of which matter for a change-feed tool.

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?

A single short sentence that is front-loaded with the verb and resource, with no wasted words. It is efficient, though the extreme brevity is a symptom of under-specification rather than disciplined concision.

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 five-parameter tool with a nested override object, no annotations, and no output schema, the description is too thin. It does not explain the return shape or the change semantics an agent needs to chain calls correctly.

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 description coverage is 100%, so each of the five parameters is already documented, including the advanced 'params' override and the Direct Client-Login override. The description only paraphrases the timestamp parameter and adds no meaning beyond the schema, making the baseline 3 appropriate.

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 states a verb ('Get') and a resource ('changes') with a temporal scope ('since a given timestamp'), so the basic purpose is inferable. But it never says what entity the changes belong to (campaigns, ads, bids?) and offers no differentiation from siblings like direct.hf.plan_changes or direct.list_campaigns, leaving the intent vague.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as plan_changes or list_campaigns. The agent is left to guess the scenario in which polling for changes is appropriate versus a full listing.

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