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

With no annotations, the descrription carries the full burden and delivvers rich behavioral context: paginated scanning across the entire days_back window, newest-first return, the window_truncaed flag semantics including which end of the window may be incomplete, and the legacy-vocabulary translation behavior with raw values preserved in object_type_raw. It also warns that extra_data is passed through untranslated, with a concrete exammple.

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 every sentence earns its place: purpose, use case, truncaion warning, then a clearly delimited VOCABULARY section. The length is justifed by the genuinely dangerous interretation trap it previents, and the critical warnings are grouped in an easily scannable structure.

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 tool with no annotations and no output schema, the descrription covers the key operational facts an agent needs: what events are returned, the ordering, the truncaion flag semantics, and the vocabulary mapping that could otherwise cause silent misanalysis. The absence of a full response-shape listing is acceptable given the descrription already surfaces every high-risk behavioral detail.

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%, setting a baseline of 3. The descrription adds genuine value beyond the schema by explaining how limit and days_back interact (scans the whole window, then returns the newest `limit` matches) and by clarifying the meaning of a returned field (extra_data.campaign_id on a create_ad event). This goes beyond the schema's per-parameter descriptions.

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 (Retrieve) plus a precise resource (change log for a Meta ad account) and enumerates the event categories (budget changes, status toggles, ad creation/deletion, billing, policy). The 'Meta' qualifier cleanly distingushes it from the sibling adsap_google_get_account_activities, and 'change log' distingushes it from get_account_summary/health.

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?

Provides a concrete, actionable use case: correlating performance drops with specific modifications (CPA spiked after a budge increase). This tells an agent when the tool is the right choice, though it doesn't explicitly name alternatives or state when not to use it.

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