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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavioral context beyond that: it is a paid surface with token costs per row, pending/error responses refund the reservation, totals are nullable with null meaning pending/unavailable (not zero), only the status section removes its own filter, and results are flattened with dimension field and truncation metadata. This is rich, non-obvious behavior that an agent needs to know.

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: it front-loads the core purpose, then covers cost, limits, return shape, null semantics, filter behavior, exclusions, and retry guidance. Every sentence carries information. It is long, but the tool is complex (49 parameters, paid surface, nuanced null semantics), so the length is justified. It loses one point for being a wall of text without paragraph breaks, which slightly reduces scannability.

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 (49 parameters, paid surface, output schema present), the description is remarkably complete. It covers cost, limits, null semantics, filter behavior, exclusions, retry guidance, and subscription category reporting. The output schema exists, so return values need not be described in detail. An agent has everything needed to call this tool correctly and avoid costly mistakes.

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 the baseline is 3. The description adds meaningful parameter-level context beyond the schema: it explains the default and maximum rows per section (10/20), which maps to max_items_per_section; it clarifies that totals are nullable and the distinction between null and numeric 0; and it notes that auto-applied subscription categories are reported in auto_applied_verticals and scope_note. It doesn't enumerate every parameter, but the schema already covers them, and the description adds the critical semantic nuances.

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 specific verb and resource: 'Get the bounded analytics overview for the current Meta /ads selection' and enumerates the exact breakdown dimensions (statuses, countries, AI categories, landing domains, advertisers, webmasters). It clearly distinguishes this from sibling search tools by emphasizing it is an analytics overview for the current selection, not a search or retrieval tool.

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 explicitly states when to use this tool: for bounded analytics on the current /ads selection, and it names exclusions: 'No pagination, sorting, source, scheduler, force-scrape, TikTok, raw SQL or storage coordinates are accepted.' It also provides operational guidance: re-issue after retry_after_seconds when pending, do not blindly retry paid calls. This is strong usage guidance.

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