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

Annotations already establish a safe read-only, closed-world lookup, so the bar is lower, and the description still adds real context: the data source (completed auction sales), the return contents (a quotable sentence plus the underlying numbers), an as-of date, and a link to the method. That provenance and freshness detail is exactly the kind of information annotations cannot carry. It does not say what happens when a model has too few or no sales, which is the main undisclosed edge case.

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 output shape is front-loaded in the first clause, then usage, then return contents, then the scope caveat. The example questions are compact and earn their place by mapping natural-language phrasing to the tool. No sentence is filler.

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?

With no output schema, the description carries the burden of describing returns, and it does so (quotable sentence, numbers, as-of date, method link). For a two-parameter read-only lookup with full schema coverage, that is nearly everything an agent needs. The only omission is behavior on sparse or zero-sale models.

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 100%, so both parameters are already documented, and the description adds only the framing that the target is a model/year range rather than an individual car. It does not explain how the optional 'make' interacts with a 'query' that already contains a make, which is the one ambiguity an agent could stumble on. Baseline 3 applies when the schema does the heavy lifting.

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 names a specific resource and output (median, 25th-75th percentile band, sale count) for a specific scope (collector-car model + year range, from completed auction sales), which is far beyond restating the name. It clarifies that it prices a model cohort rather than an individual car. It stops short of explicitly contrasting with the sibling list_models, so the agent must infer the split between 'list available models' and 'value a model'.

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?

"Use for questions like 'what is a 1989 Porsche 911 worth'" gives a concrete triggering intent, and "covers a model and year range, not one individual car" states a scope exclusion. No sibling alternative is named, so the agent gets clear context but no explicit routing rule versus list_models.

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