record_recommendations

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

With no annotations, the description must disclose behavioral traits. It only says 'record' with no mention of side effects, overwrites, idempotency, permissions, or constraints. It does not describe what happens to the data (e.g., whether it replaces existing recommendations under a run_id). For a write tool, this is a significant transparency gap.

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 main purpose is front-loaded in a concise first sentence. The second sentence is longer but still focused on workflow guidance. It could be tighter—the detail about requerying is somewhat tangential—but overall it is efficient and not padded.

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?

The tool has 3 required parameters, no annotations, and an output schema that is not described. The description lacks any explanation of parameter types or meaning, expected return values, or prerequisites. While it offers useful surrounding workflow context (cheap candidate calls, resolve_title), it does not provide enough for a correct invocation, especially given the schema coverage is 0%.

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 explain 'run_id', 'picks', and 'shortlisted'. It never mentions any of them. The terms 'seed_titles', 'genre filters', and 'exclude_title_ids' appear but belong to other tools, not this one. An agent would have no idea what to pass for 'picks' (array of objects) or 'shortlisted' (array of integers) from the description alone.

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 opening phrase 'Record only final picks' states a specific verb and resource, and explicitly contrasts with candidate exploration ('Candidate calls are cheap'), distinguishing this tool from siblings like get_candidates and discover_titles. The agent can immediately understand this is for persisting the final selection, not for searching.

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 description implies usage: this is for final picks, not candidate generation. It advises that candidate calls are cheap and suggests requerying with different seeds/filters, and mentions resolve_title for converting user words to seed IDs. However, it does not explicitly list when *not* to use this tool or name alternative tools as the preferred choice for exploration, leaving some inference needed.

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