referral_thank_you

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool writes a thank-you and mentions it does not count against a monthly draft limit, hinting at draft generation. However, it does not specify whether the tool sends the email directly, returns a draft text, or any side effects, leaving significant transparency gaps.

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 extremely concise with three substantive sentences: stating the purpose, outlining the three modes with context, and noting the draft limit benefit. Every sentence earns its place without redundancy or fluff.

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 moderate complexity (six parameters, content generation) and the lack of an output schema, the description covers the key modes and parameter nuances. It could be slightly more complete by explicitly stating the output format (e.g., 'generates a draft email'), but it is largely adequate for agent selection.

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?

The input schema has 100% description coverage, but the description adds practical guidance beyond the schema, such as explaining the nuance of the enum values (e.g., 'won_project' being the warmest) and stating defaults. It also adds context for optional parameters like 'project_type' (makes the email specific) and 'reciprocate' (offers to return the favor). This adds meaningful value for an AI agent.

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's purpose: writing a warm, specific thank-you for a referral. It distinguishes three modes (intro, had_call, won_project) which adds specificity. However, it does not explicitly differentiate from sibling tools like 'referral_request' or the similarly named 'referral_thank_you_email', which slightly reduces clarity.

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 explains the three scenarios for using the tool (intro, had_call, won_project), providing clear context. It does not, however, explicitly state when not to use this tool or compare it to alternatives like 'referral_request' or other thank-you tools. The motivational note about freelancers missing this moment is somewhat peripheral.

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