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

With no annotations, the description carries the full load and does it well: it discloses result ordering (nearest first), the exclusion of the find's own video, the distance scale (0 = identical), the fallback path for unindexed finds (matched_from), the absence of cost, and the 404 find_not_found error. It stops short of describing pagination or any rate/limit behavior beyond the limit parameter.

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?

Compact and front-loaded: the core behavior (nearest videos, ordered, self-excluded) comes first, then output semantics, then the fallback, cost, endpoint equivalence, and error. Every sentence contributes a distinct fact.

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?

With an output schema present, the description needn't enumerate return fields, and it already explains the non-obvious ones (distance, matched_from). For a 7-parameter tool the filter parameters are left to the schema, which is acceptable but leaves a small gap in how filters interact with the similarity ranking.

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 57%, and the description adds meaning for find_id (source run type) and gestures at the multiple-over-median concept, but it says nothing about type, content_type, limit, posted_within_days, or min_multiple beyond what the schema already states. Adequate but not compensating for the coverage gap.

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 and resource: nearest videos in the shared index to one of your finds, returned nearest-first and excluding the source video. That is a precise and unambiguous purpose, though it doesn't explicitly contrast with the sibling 'similar_channels' or 'search_index', so the agent must infer the boundary.

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?

It tells the agent where find_id originates (a Packaging or Long form run) and that the call is free, which implies the 'use this when you have an existing find and want neighbours' scenario. It never says when to prefer search_index, search_thumbnails, or similar_channels instead, so the routing decision is left to inference.

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