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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description adds real behavioral context beyond that: results are aggregated in one call, pet fees are computed for the entire stay rather than per night, activities are ordered nearest first, and every item carries a citation. It does not discuss truncation or how partial matches are signalled, keeping it just short of a 5.

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?

Output scope is front-loaded in the first sentence, then inputs, then sibling alternatives, then three compact examples. Every sentence carries information; the labeled example list is easy to scan and none of the examples is redundant.

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?

Eleven parameters, a nested `near` object and an output schema are all accounted for: the description tells the agent what the response contains by section, which inputs are needed, and when a sibling is a better fit. With annotations covering safety and the output schema covering return shape, nothing an agent needs in order to invoke this correctly 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?

Schema description coverage is 100%, so the baseline is 3, but the description goes beyond it by demonstrating how conversational phrasing maps onto argument values ('a weekend' to nights=2, 'two small dogs' to dogs=2, an area name substituted for a town plus stay_types). That mapping guidance is genuine value the schema cannot supply, though most individual parameters are still left to the schema.

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 and resource ('Plan a stay ... with a dog, in one call') and enumerates the three sections produced (stay with pet fee for the whole stay, dog-friendly things to do nearest-first, dog-friendly patios), each with citations. An agent can distinguish this from dogpolicies_near or dogpolicies_find_hotels without opening a schema.

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?

Explicit routing: use dogpolicies_route_stops for the drive and dogpolicies_near for a quick list without the stay check. It also states the required inputs (town or county plus dog weight, dog count, nights, fee cap) and shows three worked request-to-argument mappings, including the non-obvious one mapping 'camping near Mammoth Lakes' to place="Mono County".

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