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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds a lot beyond them: exact-name matching with a candidates fallback, no spend data on live lookups, a paid-plan requirement, live-lookup limits per conversation and per day, and no sign-in for tracked brands. These are precisely the operational constraints an agent needs before committing a call.

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?

Front-loads the identity and scope in the first clause, then moves from return contents to matching behavior to the live_lookup escape hatch in a logical order. The return-field list ('image or video, headline, text, days running, platforms and landing domain') is dense and slightly enumerative, but each item tells the agent what it can answer for the user.

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?

There is no output schema, so the description must carry the return shape, and it does in detail, including the degraded candidate response and the reduced live-lookup response. Between the schema, the annotations and this text, an agent has enough to call it correctly and set user expectations on the first attempt.

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 per-parameter definitions already do the heavy lifting and the baseline is 3. The description still contributes cross-parameter meaning: page_id is preferred over brand when known, and live_lookup is only justified after a prior candidates response. Those relationships are not purely restatements of the individual schema fields.

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 and resource ('Show one brand's active Meta ads (Facebook and Instagram)') and enumerates what comes back: active ad count, 30-day spend range split EU/UK vs US, and up to six top ads with creative fields. That detail effectively separates it from stats-style siblings like get_top_ads_stats. It never names or contrasts the closest siblings (list_brand_ads, get_ad_details, find_similar_advertisers), so the boundary is inferred rather than stated.

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 real routing rules: 'Pass page_id when known, otherwise brand', and the negative case that a non-exact brand name returns candidates and no ads. It also gates live_lookup tightly ('True only after a previous call returned candidates and none is the brand the user means'). It stops short of saying when to prefer this tool over list_brand_ads or find_similar_advertisers outright.

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