Update keyword

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the bar is lower. The description adds the cross-tool provenance rule for location_key, but is silent on whether this is a partial patch, what passing null does to an existing field, or that idempotency_key exists for retry safety.

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 tight sentences with the core purpose front-loaded and the dependency caveat second. No filler, though the @language clause restates what the location_key schema description already says, so that half-sentence does not fully earn its place.

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 mutation tool with a nested schedule object and no output schema, the description covers the highest-risk parameter (location_key) and its cross-tool source, which is the biggest trap. It is still thin on null-to-clear semantics, on the country/city/location/location_key hierarchy, and on partial-update behavior.

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 only 40% across 15 parameters, so the description has to carry weight. It names roughly six fields (keyword, country, device, target_url, tags, schedule) and explains location_key plus the @language qualifier, but leaves city, location, topic, intent, frequency, project_id and idempotency_key unexplained, and never disambiguates the four location-ish fields (country, city, location, location_key).

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 ("Update keyword metadata") and enumerates the mutable fields (text, country, device, target URL, tags, schedule), so an agent knows exactly what the tool touches. It does not, however, distinguish itself from siblings like bulk_update_keywords or set_keyword_target_url, which overlap on the same resource.

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 one explicit routing instruction is genuinely useful: "Use search_locations and pass its location_key verbatim" tells the agent where the location value must come from. Beyond that, there is no when-to-use or when-not-to-use guidance, and no signal for choosing this over bulk_update_keywords or set_keyword_target_url.

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