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

Annotations declare readOnlyHint=true and openWorldHint=true, so the agent already knows this is a safe, non-mutating operation. The description adds valuable behavioral context: it produces exactly two texts, enforces a length limit, and imposes content rules (one question, a way out, no price/payment/discount). This goes beyond the annotations and helps the agent set expectations. It does not mention output format, but with no output schema, that is a minor gap.

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 a single, dense sentence that front-loads the core action ('Writes two follow-up texts') and then lists the key constraints in a compact, scannable list. Every phrase earns its place; there is no filler or repetition of schema field names.

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?

For a generation tool with no output schema, the description covers the essential behavioral contract: what it produces, how many, length limit, and content constraints. It does not specify the output format (e.g., plain text vs. structured list), which an agent might need to know, but the constraints are detailed enough for most use cases. The openWorldHint annotation also signals that the tool may accept flexible inputs, which the description supports by saying 'a sales situation you describe.'

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 only 17% (only 'situation' has a description), so the description must compensate. It does: it explains that the tool takes a sales situation and produces texts with specific constraints. However, it does not clarify the meaning of parameters like 'rep', 'company', 'product', 'day_and_time', or 'customer_first_name' beyond their names. The description's content rules (names the rep and company) imply some parameter usage, but explicit mapping would be stronger.

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 ('writes'), a specific resource ('two follow-up texts'), and the exact context ('for a sales situation you describe'). It also lists concrete content constraints (under 300 characters, names rep and company, one question, a way out, no price/payment/discount), which makes the tool's purpose unmistakable and distinguishes it from siblings like rewrite_follow_up_text or check_follow_up_text.

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 clearly implies when to use this tool: when you need to generate two follow-up texts for a sales situation. It does not explicitly name alternatives or exclusions, but the sibling list includes rewrite_follow_up_text and check_follow_up_text, and the description's focus on 'writes two' makes the use case clear. It could be improved by explicitly saying 'use rewrite_follow_up_text to revise an existing text' or 'use check_follow_up_text to evaluate a text.'

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