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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to spend its words on non-obvious result behavior — and it does: the match/possible/excluded bucketing rules, what elevates a hotel to 'possible', and the sort order (matches first, cheapest pet fee first). That is output behavior an agent could not infer from the schema and is exactly the kind of context that changes how results should be reported to a user.

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?

Front-loaded one-sentence purpose, then the ranking/eligibility semantics, then four examples that each exercise a different parameter path with no redundancy. Every sentence earns its place and no example repeats another's parameter combination.

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 15-parameter tool with a nested object, four enums and an output schema, the description covers scope, eligibility semantics, ordering and query-to-parameter mapping well. The remaining gap is modest: no mention of how the sibling lookup/planning tools relate, and no note that the underlying policy data can change (relevant given the changes_since/changes_near siblings).

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 schema already carries the per-parameter burden. The description still adds genuine value by demonstrating how free-form traveler questions decompose into parameter combinations (county vs. near vs. query vs. county+state, plus dogs/nights feeding the fee estimate), which the schema alone does not teach.

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 (find hotels/motels) plus the two filters that matter most: pet-friendly for a specific dog and pet fee for the stay, scoped to California and Nevada. This is clearly distinct from siblings like search_places, get_place or plan_trip, which operate on places/policies rather than answering a lodging question.

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 four worked examples give concrete when-to-use signals across the main query shapes (county + weight + budget, point proximity + party size, name lookup, county + state). What's missing is an explicit steer on when to prefer a sibling such as dogpolicies_search_places, dogpolicies_plan_trip or dogpolicies_compare_places instead, so the boundary with siblings is left implicit.

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