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

Annotations already declare readOnly and non-destructive. The description adds valuable behavioral details: score and decision are always included, empty sections returns everything, and the filter options. This goes beyond the structured annotations.

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 efficient and structured. The main capability is stated in the first sentence, followed by a concise list of return contents and a clear Args section. No wasted words.

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 simplicity (2 params, read-only), the description covers everything an agent needs: input origin, filter options, always-included fields, and return content. The output schema further reduces the need to describe return structure.

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 has zero descriptions, and the description fully compensates by explaining deal_id's origin and sections semantics (comma-separated, options, behavior). This adds substantial meaning beyond the bare 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 clearly states the tool retrieves full results of a completed Sieve analysis, listing specific outputs (score, decision, summary, strengths, concerns). It distinguishes itself from sibling tools like sieve_screen (which produces the deal_id) by focusing on post-analysis result 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?

It provides clear context: use after a completed Sieve analysis, with a deal_id obtained from sieve_screen. However, it does not explicitly name alternatives or when-not-to-use, though the 'completed' qualifier implies not for ongoing analyses.

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