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

With no annotations, the description takes on the safety burden and handles it well: it warns that 'This sends a real email' and instructs confirmation, flagging the side effect and requiring consent. It does not cover auth, retries, or failure modes, but the key externally visible behavior is disclosed.

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?

Three sentences with each earning its place: the action, the exact id/email requirements, and the confirmation warning. The most important operational constraint is front-loaded and there is no filler.

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 10-parameter side-effecting tool with no annotations or output schema, the description covers the prerequisite search, required id provenance, email acquisition, and confirmation step. The schema documents the remaining parameter semantics, so nothing needed to invoke correctly is missing.

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 the baseline is 3; the description adds meaningful guidance by requiring the ids 'exactly as search_flights reported them' and telling the agent to ask for the email and never invent one. That clarifies the provenance and handling of the most safety-critical parameters.

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 opens with a specific verb and resource: 'Email one of the options returned by search_flights to the traveller as a formal offer.' It names the source of the data and the purpose, which makes the operation unambiguous and distinguishes it from search_flights and request_group_quote.

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 gives clear operating context: the tool is used after search_flights, the ids must be copied exactly, the email must be obtained first and not invented, and the traveller must confirm before a real email is sent. It does not explicitly say when to prefer a sibling alternative, but the context is strong enough to route the agent correctly.

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