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

Annotations already cover readOnly, idempotent, and openWorld hints. The description adds valuable context: the memo can be null for most leads, the content is raw outreach material, and the null case should not be treated as an error. This goes beyond annotations and clarifies expected behavior. It does not contradict 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 longer than minimal but every sentence earns its place: it defines the memo, gives the usage directive, and explains the null case. It is front-loaded with the core purpose and then addresses behavior. While not ultra-terse, it avoids fluff and is structured logically.

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 doesn't need to detail return format. It covers the key edge case (null memo), the expected usage in the outreach workflow, and the fallback. For an agent deciding when to call this tool and how to interpret the result, the description is complete.

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 description coverage is 100%, so the leadId parameter is already well documented. The description does not add new meaning to the parameter, just refers to it implicitly. Baseline 3 is appropriate given the schema fully covers it.

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 a research memo for a single lead, describes the memo's typical content, and distinguishes it from scoreExplanation. It is specific about the resource and purpose, and the mention of rewrite_outreach differentiates it within the workflow context.

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?

Explicitly instructs when to use it ('before calling rewrite_outreach'), how to use the result (build outreach around a specific fact), and what to do when the memo is null (fall back to scoreExplanation, do not invent details). It also flags that null is common, not an error. This is thorough guidance.

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