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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the description is not burdened by safety disclosure. It adds real context: one page per call (pagination implied via offset/limit), a per-result one-line answer, a yes/yes_restricted/no/varies status vocabulary, a verification date and page URL, and the hard CA/NV coverage limit that annotations cannot express.

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 with purpose, then return shape, then a compact example block; the structure matches how an agent scans for selection then invocation. The example list is long and a couple of entries overlap in what they demonstrate (park-type plus county/state), but each still teaches a distinct filter combination for a 12-parameter tool.

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 12-parameter, nested-object search with an output schema present, the description supplies scope, return contract summary and invocation examples, which is close to sufficient. Missing only the sibling-routing rule and filter-precedence guidance that would make zero-parameter guesswork unnecessary.

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 coverage is 100%, so baseline is 3; the examples push it higher by showing how filters combine ('Lake Tahoe beaches in Nevada that allow dogs' -> type+state+dogs_allowed) and by mapping colloquial phrasing onto 'query'. It does not clarify precedence when 'near', 'area' and 'region' are supplied together, which is the main remaining ambiguity for a 12-parameter 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 ('Search parks, beaches, trails, hotels, campgrounds and cabin resorts in California and Nevada') plus the filterable facets (name, location, dog rules). The geography restriction and covered place types make it distinguishable from generic siblings, though it never explicitly names which sibling handles single-place lookup or hotel-only search.

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 eight query-to-parameter examples effectively teach when this tool is the right choice, showing that natural-language trip questions map onto combined filters. Gaps: no explicit exclusions (e.g., 'for a single known place use dogpolicies_get_place', or when to prefer dogpolicies_near), so the agent must infer the boundary.

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