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

Annotations only say readOnlyHint=false, idempotentHint=false, destructiveHint=false. The description goes well beyond that: it explains the side effect is an email with a 30-minute confirmation link, that nothing is reserved, that the slot remains available to others, and that only the recipient's click commits the booking. That is exactly the non-obvious behavior an agent needs.

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?

Front-loaded with the core action, then the critical caveat. Every clause carries information, though the second sentence is dense and packs the thirty-minute validity, the click requirement, and the open-slot warning into one run-on.

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 no output schema, the description correctly explains the observable outcome (email sent, nothing booked, slot still open) so the agent knows what to tell the user. It does not cover failure modes such as an invalid email or a slot taken between check and request, which would round out a 7-parameter mutation tool.

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 86%, so the schema already documents nearly every parameter (including that start comes from check_availability and that email receives the confirmation). The description adds no syntax, format, or default information beyond that, so the baseline 3 applies.

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?

States a specific verb and resource ('Propose a booking') and immediately draws a hard boundary against what it is not ('does NOT book anything and does NOT reserve the time'). The confirmation-link mechanic makes it unmistakable from siblings like check_availability or submit_project_inquiry.

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?

Gives clear operational context: the slot stays open, the person must click within thirty minutes, and the agent should tell them to expect the email. It stops short of explicitly naming an alternative tool or a prerequisite step (e.g. call check_availability first, which only appears in the schema), so it is strong context without explicit sibling routing.

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