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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description layers on substantial behavior the annotations cannot convey: default filtering to active ads, sort default, row compaction, null semantics for headline/body, truncation at 140/280 characters, and the caveat that spendEstimate is an engagement-based estimate with spendLowerBound meaning a floor.

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?

Dense but front-loaded: the purpose and default behavior come first, then row semantics and caveats. Every sentence carries information, though the paragraph is long and a few clauses (truncation vs get_ad) could be split for scanning.

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?

With 11 optional params, nested tag objects and no output schema, the description compensates well by describing row shape, field provenance, truncation behavior and estimate semantics. An agent has what it needs to call it correctly and interpret the results.

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 baseline is 3, but the description adds real meaning: it ties the tags dimensions/slugs to list_taxonomy's output as the valid source, and clarifies that adKey from rows is what get_ad and get_swipe_prompt accept. That elevates it above the schema-does-everything baseline.

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 (search the Ad Radar library of FB/IG ads from the Meta Ad Library) and scopes it with a concrete qualifier ($50k+ estimated spend). It distinguishes itself from siblings by naming get_ad, get_swipe_prompt and list_taxonomy and explaining how each relates.

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?

Gives clear context: default is active-only, sorted by score, compact rows; use get_ad for full untruncated text; use list_taxonomy for valid tag dimensions/slugs; adKey feeds get_ad and get_swipe_prompt. It stops short of explicit when-not/exclusion guidance, but the routing to alternatives is unambiguous.

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