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

Annotations only carry the generic safety profile (write, non-idempotent, non-destructive, closed-world), while the description adds genuinely new facts: it requires the geo:write scope, it does not trigger sampling, it does not debit the wallet, and the quote expires. That side-effect disclosure is exactly what annotations cannot convey. It stops short of saying whether a repeat call issues a new quote or reuses one.

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 tight sentences, front-loaded with the action verb, then the auth prerequisite, then the side-effect negation, then the UX constraint. No filler, and the ordering matches how an agent needs to reason about the call.

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 non-idempotent write tool with no output schema and no meaningful annotation detail, the description does well on workflow and side effects ('show the quoted amount, scope and expiry' implies the return payload). However, the undocumented required parameters and the absence of guidance on quote lifetime or reuse leave real gaps an agent must guess at.

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 0% across 8 parameters, so the description carries the whole burden, yet it only names target/questions/repeats. Critical inputs such as max_unit_cents (the price ceiling that governs a quote), source_check_id, revision and product go unexplained, leaving over half the parameters undocumented in both schema and text.

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 ('Create an expiring quote for a customer-owned project') with the scoping inputs (target/questions/repeats) named in the same sentence. It also implicitly routes the agent away from the sampling/accept step via 'Does not start sampling', so it is distinguishable from siblings like geo_accept_observation.

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?

'Does not start sampling or debit the wallet' plus 'Show the quoted amount, scope and expiry before acceptance' tells the agent this is the pre-acceptance step and that acceptance comes later. It gives clear context but never names geo_accept_observation explicitly as the follow-up, so the when-to-use is inferred rather than stated.

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