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

Annotations cover read-only, open-world, idempotent, and destructive flags, so the safety profile is already handled. The description adds real behavior beyond them: it reserves credits (a side effect with cost implications) and kicks off external collection, which an agent needs to know before invoking.

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 short sentences, front-loaded with the gating condition, followed by effect and the idempotency instruction. No filler, though "Reuse the idempotency key" is a terse fragment that could be slightly clearer as guidance.

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?

An output schema exists, so return values needn't be described, and annotations cover the mutation/idempotency profile. The precondition and credit-reservation behavior are present; the main remaining gap is the undocumented required parameters.

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 4 required parameters, so the description must carry the load. It only loosely touches maximumCredits and idempotencyKey, and says nothing about brandId or quoteId (e.g., where the quoteId comes from), leaving half the required inputs unexplained.

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?

Clear verb+resource ("Start research") with a stated precondition (user has accepted the quote) that separates it from the quote/prepare phase. It does not explicitly name the sibling quote_research or cancel_research, so sibling differentiation is implied rather than stated.

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?

"Start research only after the user accepts the exact quote and maximum credits" gives a concrete gating condition — a strong when-to-use signal. It stops short of naming the alternative (quote_research) the agent should call first to obtain that quote, so it isn't a full when/when-not/alternative statement.

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