advanced_title_search

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

Annotations already declare readOnly/idempotent/non-destructive/open-world, so the safety bar is met structurally. The description adds genuinely useful behavior: keyset pagination via next_cursor, per-page limit, sort field vocabulary, and the AND semantics of keywords ('all required'). No auth or rate-limit notes, but nothing expected is missing for a read-only search.

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?

Purpose and a concrete example are front-loaded in two sentences, followed by an Args block that is justified by the 0% schema coverage. Each line is one clause with no marketing padding; the only mild redundancy is that some lines restate the parameter name.

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 13-parameter all-optional search with an output schema covering return shape, the description is close to sufficient: filters, sorting, and pagination are all addressed. The one meaningful hole is the absence of any statement about whether at least one filter is required or how filters combine (AND vs OR) when several are supplied.

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 0%, so the description carries the full burden and largely delivers: every one of the 13 parameters gets a line, with allowed values for title_types, sort and order, and a range (1–10) for min_rating. Gaps remain — the genre list is only illustrative ('as IMDb spells them') and there is no hint of defaults or of combining multiple genres.

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 (search) and resource (titles) plus the dimensions it can filter on, and the IMDb 'advanced search' framing distinguishes it in spirit from the plain search_titles sibling. However, it never names search_titles or get_result_page, so the boundary between 'advanced' and simple search is left implicit.

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 worked example ('best rated horror films of the 1970s with over 10,000 votes is one call') makes the intended compound-filter use case clear. But there is no explicit routing guidance — nothing says when to prefer search_titles or get_result_page, or whether zero filters is a legal call.

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