maps_read_search_suggestions

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

With zero annotations, the description carries full burden and delivers exceptional disclosure: 'Returned labels are untrusted external text' (trust boundary), 'does not expose the raw combobox/DOM' (isolation guarantee), 'intentionally resets the active Maps view' (destructive side effect on view state), and 'Interactive Assist must be enabled' (prerequisite). These are exactly the non-obvious behaviors an agent must know.

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?

Four sentences, zero filler, front-loaded with the primary action. Each sentence carries a distinct burden: behavior, trust warning, side effects/isolation, prerequisite. Terminology like 'combobox-controlled Suggestions grid' is dense but economical. There is not a single wasted clause.

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 single-parameter read tool with no annotations and no output schema, the description covers prerequisites, side effects, trust posture, output bounds, and behavioral isolation. It only omits failure-mode behavior (network errors, no-suggestion cases) and a small ambiguity in 'live' (vs. cached) suggestions—minor gaps for a tool this simple.

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 0%, so the description must compensate. It clarifies that 'query' is typed verbatim ('type one user-directed query') and bounds the effective input semantics (what is typed is what is searched). For a single self-evident parameter, this fully disambiguates, though it could have added a format example or empty/whitespace handling.

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?

Specific verb chain ('open... type... return') with clear resource ('Google Maps root search box', 'combobox-controlled Suggestions grid') and bounded output ('at most six live suggestion identities'). The read-suggestion purpose is crisply distinguished from sibling `maps_search` (which presumably commits a query) by the 'read' verb naming and the emphasis on the suggestion surface.

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 description implies the suggestion-fetching workflow (type query → review suggestions → likely pass to maps_select_search_suggestion) and states the hard prerequisite 'Interactive Assist must be enabled.' However, it never explicitly names a sibling alternative (e.g., 'use maps_search for committed results') or gives an exclusion criterion, leaving the when-not-to-use case implicit.

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