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

No annotations are provided, so the description must disclose behavioral traits fully. It explains the internal logic: building a feature vector, scanning a window, and using cosine similarity (1.0 = identical). It states the output ordering (highest similarity first) and uses the term 'returns the top matches.' It does not cover error cases, performance, or data source, but for a search tool this is adequate.

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 description is three sentences with no wasted words. The first sentence states purpose, the second explains the method, and the third gives the user question and output format. It is front-loaded and every sentence earns its place.

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 5 parameters and no output schema, the description is fairly complete. It explains the input (reference_date, start, end, step_days, limit), the process (feature vector, cosine similarity), and the output (top matches with similarity, highest first). It could mention edge cases like empty windows or invalid dates, but overall it provides sufficient context for an AI agent to invoke the tool correctly.

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 100%, so baseline is 3. The description adds meaning beyond the schema by explaining the algorithm (cosine similarity), how the reference_date is used as a target, and that results are ordered by similarity. It also clarifies the roles of start/end as a search window and step_days as sampling. This adds interpretive value.

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 uses a specific verb ('Find') and resource ('sky') and clearly states what the tool does: finding when the sky most resembled a reference moment. It explains the algorithm (cosine similarity) and answers a natural language query ('when did the sky last look like this?'). This distinguishes it from sibling tools like current_sky or sky_events, which focus on current or future configurations.

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 gives clear context for when to use this tool: for transit echoes and historical analogues. It phrases the user's question ('when did the sky last look like this?') as an explicit usage hint. However, it does not mention when not to use it or list specific alternatives among the 34 sibling tools.

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