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

The deprecation disclosure ('old', 'v1') is significant behavioral context that annotations don't convey — it tells the agent this tool is obsolete and should be avoided. readOnlyHint=true is consistent with a read operation and is not contradicted. What's missing is whether calling it still succeeds or errors, but the deprecation flag itself is valuable.

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?

Two short sentences with the deprecation warning front-loaded ahead of the alternative tool. Extremely economical for its purpose. It loses a point only because it's so minimal that it borders on under-specification — but for a deprecation stub, this is near-ideal conciseness.

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 tool with 5 parameters and no output schema, the description covers the essential facts: it's legacy, and want should be used instead. It omits what happens if the tool is called anyway (success vs error) and doesn't clarify that parameters are irrelevant. This is adequate but not complete for an agent that might encounter this tool in legacy data.

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%, so the description carries full responsibility for parameter meaning, yet it explains none of the five parameters (note, category, provider, monthly_cap_usd, min_discount_pct). Since the tool is deprecated and the agent is told to use want instead, parameters may be moot, but by the rubric the gap is severe — no semantic help is provided.

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 identifies this as 'The old v1 park' and instructs using 'want' instead, but never actually states what parking a standing order accomplishes. For an agent encountering this tool cold, the core action is undefined — it only knows it's a deprecated alternative to want. The reference to sibling 'park' is a shorthand that assumes prior knowledge.

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 instruction 'Use want with a link instead' is explicit routing to a sibling tool, which is strong guidance for a deprecated entry point. It clearly implies this tool should not be called. It doesn't elaborate on when want is preferred over other siblings like hold or waitlist, but for a deprecation notice the routing is sufficient.

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