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

With no annotations, the description carries the whole burden and does well: it discloses concrete side effects (signing links stop working, follow-ups stop) and irreversibility ('cannot be reopened'). What it leaves out is the operational envelope — required permissions, whether the customer is notified, and what happens if the quote turns out to be signed — so a mutation agent still has unanswered questions before calling.

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 action and scope, then side effects, then the irreversibility warning and fallback. No sentence repeats the name or the schema, and the final sentence doubles as both constraint and alternative.

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 two-parameter mutation with an output schema (so return values need no explanation) and no annotations, the description supplies the essential behavior: what stops working, that it's terminal, and what to do next. The remaining gap is failure/permission semantics for the undocumented quote_id, which keeps it below fully complete.

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 50%: 'reason' is self-documented in the schema as optional, max 500 chars, and not shown to the customer, which the description only echoes. 'quote_id' has no schema description at all, and the description doesn't clarify that it must reference an unsigned draft/sent quote or what happens if it points elsewhere. Baseline 3 is appropriate given partial coverage.

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 (withdraw) applied to a specific resource (quote) and narrows the scope to drafts or sent quotes that are unsigned. An agent can distinguish this from quotes_revise or quotes_create without opening any schema, because the description makes clear this is a state-terminating action, not an edit or a new document.

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 precondition ('a draft or sent quote the customer has not signed') tells the agent when the tool is applicable, and the closing line 'create a new quote if needed' points at the correct alternative path after withdrawal. It stops short of naming quotes_revise as the alternative when the intent is to change rather than kill a quote, so the routing guidance is clear but not exhaustive.

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