Add keywords

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

With annotations present (readOnlyHint=false, destructiveHint=false), the description is not contradicting them. It adds the useful note about passing location_key verbatim for city-level tracking. However, for a mutation tool with rich nested objects (schedule, location, device, intent, topic), it does not disclose side effects like whether existing keywords are deduplicated, whether rank checks are triggered on add, or idempotency behavior via idempotency_key. The description carries the burden but stays minimal.

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?

Two sentences, zero filler. The first sentence states the core function and optional parameters; the second gives actionable workflow guidance. Every word earns its place, with no redundancy.

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?

Given the tool's complexity — 13 parameters, nested keyword objects with per-item schedules/device/location, no output schema, 31% schema coverage — the description is incomplete. It doesn't explain return value/behavior (does it return created keyword IDs?), per-keyword vs bulk parameter overriding rules, or the meaning of intent/topic/device. Annotation coverage is minimal (no openWorldHint info given as context). The description does the minimum but leaves significant gaps for such a complex tool.

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 low at 31%, with 13 parameters and nested objects. The description does compensate partially by naming the key optional enrichments (tags, target URL, schedule) and by highlighting location_key's critical role. However, many parameters (topic, intent, device, country, city, location, idempotency_key) lack schema descriptions, and the description doesn't explain their meaning, so the burden isn't fully met despite the good location_key guidance.

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 clearly states: 'Add one or more keywords to a project, optionally with tags, target URL, and schedule.' It uses a specific verb + resource, enumerates the optional attributes, and adds the specific instruction to use search_locations and pass its location_key verbatim. This distinguishes it from siblings like bulk_update_keywords and update_keyword.

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 provides a concrete usage pointer: 'Use search_locations and pass its location_key verbatim for city-level tracking.' This tells the agent the recommended prerequisite and workflow. However, it doesn't explicitly state when NOT to use this tool (e.g., vs update_keyword or bulk_update_keywords), though the verb 'add' semantically implies creation.

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