get_change_history

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It discloses the date range policy (29 days before today through today), the LIMIT 1000 cap, the possibly_truncated signal on every local page, the fact that local tokens cannot recover beyond the cap, and the upstream maximum LIMIT 10000. It also clarifies the end-date boundary behavior (including fractional seconds, up to but excluding the next calendar day's midnight). This is rich behavioral context that an agent needs to handle pagination and truncation correctly.

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 description is dense but well-structured, front-loading the core purpose in the first sentence and then layering constraints and edge cases. Every sentence adds meaningful information about date handling, pagination, truncation, or alternatives. It is longer than average, but the complexity of the tool (date boundaries, pagination caps, truncation signals) justifies the length. A slight deduction for the density of the truncation explanation, which could be more scannable, but overall it earns its place.

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's complexity (date range semantics, pagination, truncation, upstream limits) and the absence of both annotations and an output schema, the description is remarkably complete. It covers the key behavioral aspects an agent needs to call the tool correctly: date format, date range, time zone, end-date boundary, LIMIT 1000, possibly_truncated signal, token limitations, and the alternative run_gaql for larger queries. The only minor gap is the lack of explicit description for optional parameters like customer_id and resource_type, but the overall context and schema structure make their roles inferable.

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 0%, so the description must compensate for the schema's lack of parameter documentation. The description explains the date range semantics (strict YYYY-MM-DD, inclusive from 29 days before today through today) and the LIMIT 1000 behavior, which directly informs how date_range_start and date_range_end should be set. However, it does not explicitly describe page_token, customer_id, or resource_type parameters, though the overall context implies their roles. Given the 0% coverage, the description adds substantial meaning for the required parameters but leaves some optional parameters undocumented.

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 clear, specific verb and resource: 'Who changed what, when, with which client: change events with actor email, client type, and old/new values per changed field.' This precisely states what the tool returns and distinguishes it from sibling tools like get_campaign_performance or get_ad_performance, which focus on performance metrics rather than change history.

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 provides explicit usage guidance: strict YYYY-MM-DD dates, inclusive from 29 days before today through today in the verified account time zone, and a LIMIT 1000 with a note that more than 1000 events may need a different run_gaql query. It also distinguishes this tool's local 30-calendar-date policy from provider sub-day retention, and explicitly mentions when to use run_gaql as an alternative for larger result sets.

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