discover_titles

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

With no annotations, the description carries full behavioral burden and does so well. It discloses exclusion rules ('Seen, rated, and not_interested titles are excluded unless allow_repeats applies; not_interested stays excluded'), the default vote floor ('the default floor is 1000 votes for movies and 500 for TV'), and cost/paging behavior ('Calls are cheap and paging is normal'). No contradictions.

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?

Three sentences, no fluff. Purpose is front-loaded, then usage context, then edge-case behavior. Every sentence adds value and the description is compact for a 13-parameter tool.

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?

Given the tool's complexity (13 params, output schema present), the description covers the most important behavioral aspects: exclusion rules, default thresholds, and chaining to get_candidates. It does not explain how filters combine (AND/OR) or what happens with no results, but these are minor given the output schema and the simplicity of the tool's purpose.

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 0%, so the description must compensate. It maps main filter categories (era→year_from/year_to, genre→include/exclude_genres, rating→min_vote_average, language→original_language, keywords→keywords) but does not explain several parameters (page, sort_by, audience, allow_repeats, min_vote_count). Those are self-explanatory from names, but the description adds only partial value over the schema.

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 states a clear verb ('Find') and resource ('titles') with a specific set of filters: era, genre, rating, language, keywords. It also distinguishes itself from similarity search by saying 'use this when similarity search cannot express the user's request,' which differentiates it from siblings like get_candidates and resolve_title.

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?

Explicitly provides when-to-use guidance: 'Use this when similarity search cannot express the user's request.' It also explains how results can feed into another tool: 'Results can be passed to get_candidates as seed titles.' This is clear and actionable for an agent choosing between tools.

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