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

The description adds critical behavioral guidance beyond the annotations by warning to read the returned BAND rather than the raw cosine and quantifying the score distribution (43% of the corpus sits at 0.80–0.90 by default). This prevents a common misinterpretation of the output and is genuinely valuable context.

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?

Two concise sentences: the first states the core action and resource, the second delivers a crucial interpretation warning. Every word earns its place, and the most important usage caution is front-loaded.

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 is simple (one parameter, rich annotations, no output schema), and the description covers the essential behavior and output interpretation. It could be slightly more complete by explicitly describing the returned structure beyond 'BAND' and 'raw cosine', but for this complexity level the gap is minor.

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?

With schema description coverage at 0%, the description must compensate. It minimally clarifies that post_id refers to the 'given post' used as the reference for similarity, but it does not explain how to obtain a valid post_id or what happens for invalid IDs. The schema's type and title already convey the basic meaning, so the added semantic value is modest.

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 specific verb ('nearest'), a resource ('posts'), and the method ('embedding space'), making it clear this is a similarity-search tool. It distinguishes itself from siblings like get_social_posts or get_story_posts by emphasizing embedding proximity rather than simple retrieval.

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 is implied: use this when you need posts similar to a given post in embedding space. However, it does not explicitly mention alternatives or conditions when this tool should be preferred over sibling retrieval tools, so the guidance is only implicit.

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