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

Beyond the annotations (readOnly=false, destructive=false, non-idempotent), the description discloses that the confirmation flag is ignored, that no charge occurs, that an approval_url is returned, that the tool sunsets 12 months after the new tools launch following three notices, and it documents the PECR default exclusion of sole traders/partnerships. This is unusually rich behavioral context that annotations alone would never convey.

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?

The deprecation and migration guidance is correctly front-loaded, but the text degenerates into long semicolon-chained run-ons, and the closing sentence on UK GDPR lawful basis and PECR audience defaults, while compliance-relevant, does little to help an agent decide or invoke. It is informative but bloated for a deprecated shim.

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 deprecated, zero-parameter tool with an output schema, the description covers what an agent needs: don't use it, use these instead, it is now a quote that charges nothing, and it returns approval_url. The migration URL and sunset window round it out; nothing essential 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?

The tool takes zero parameters, so the baseline is 4. The schema description already explains that the arguments are the old tool's, unchanged, with an adapter mapping them and a migration doc enumerating them; the main description adds no parameter detail but none is needed.

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 immediately labels itself 'Deprecated' and resolves the name/title mismatch by stating what a call actually does now: it 'makes a machine quote for the list' and no longer spends credits. That is a specific, actionable statement of current behavior, though the tool's identity ('create_data_extract' vs 'create an order' vs a quote) remains slightly muddled for an agent scanning names alone.

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 names the exact alternatives and order of use: 'Use quote_order, then create_order instead.' It also spells out the conditions under which the old path still matters (user confirmation in a form/site, or an agent key covering the spend within limits) and what happens otherwise (nothing charged, approval_url returned). That is explicit when/when-not guidance.

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