search

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

Without annotations, the description carries the full burden. It does disclose the optional access_token behavior (cached token fallback) and the return format (JSON with matching record IDs). However, it does not mention that the search is read-only, nor does it clarify matching semantics (exact, partial, fuzzy) or potential rate limits/pagination, leaving behavioral gaps.

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 well-structured with Args, Returns, and Example Usage sections. It is not overly long, though the five example usage lines are somewhat redundant. The key information is front-loaded in the first two sentences, and every section serves a purpose.

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 search tool with two parameters and an output schema, the description provides a decent overview. It states the return format (list of matching record IDs) and supports examples. However, it lacks details on result limits, pagination, or how search results are ranked/ordered, which are common concerns for search tools. The existence of an output schema reduces the need to explain return values, but behavioral aspects like result boundaries remain uncovered.

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?

The input schema only provides types, with 0% description coverage. The description compensates by explaining 'query' as a search query string to find relevant records and 'access_token' as an optional token with cached fallback. This adds meaningful context beyond the schema, though it could be more detailed about query syntax or accepted values.

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 clearly states 'Search through Meta Ads data and return matching record IDs' with a specific verb and resource. It further specifies the scope by listing ad accounts, campaigns, ads, pages, and businesses, distinguishing it from the more specific sibling search tools like search_pages_by_name or search_ads_archive.

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?

Usage context is implied through examples like 'search(query="active campaigns")' and 'search(query="user businesses")', which show cross-entity searching. However, there is no explicit guidance on when to use this generic search versus the dedicated sibling search tools, nor any exclusions for when it is not appropriate.

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