Update keyword

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

Annotations declare readOnlyHint=false (mutation) and destructiveHint=false, so the description's 'update' semantics align with annotations — no contradiction. However, the description adds limited behavioral context beyond the annotations: it does add the location_key provenance detail ('pass verbatim'), which is a useful behavioral note. It doesn't disclose partial-update semantics (whether omitted fields are preserved or cleared) or auth requirements, which given 15 optional params would be valuable.

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, tightly scoped, front-loaded with the core purpose. The first sentence lists the mutable fields; the second gives the key usage prerequisite. Every clause earns its place with zero filler.

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 15 params, a nested schedule object, and no output schema, the description is lean. It competently covers the core purpose and the location prerequisite, but doesn't address ambiguities the schema leaves open: difference between 'frequency' (top-level) and 'schedule.frequency', partial-update behavior for nullable fields (city, country, target_url accept null — implying clearing), or project scoping. For a high-parameter mutation tool, the description should resolve some of these.

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 only 33%, so the description partially carries burden. It maps fields (text, country, device, target URL, tags, schedule) to parameters, which adds value. The location_key verbatim instruction adds genuine semantic detail beyond the schema's regex pattern. However, many parameters (intent, topic, project_id, idempotency_key, frequency vs schedule) lack description coverage, and the description doesn't clarify the relationship between the top-level 'frequency' and the nested 'schedule' object.

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 'Update keyword metadata such as text, country, device, target URL, tags, or schedule' — a specific verb+resource with enumerated field examples. It also distinguishes from siblings by referencing search_locations for location handling, differentiating it from set_keyword_target_url (which is a more narrow single-field update).

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 clear usage hint: 'Use search_locations and pass its location_key verbatim for city-level tracking.' This names a specific companion tool and explains the prerequisite for location. It doesn't explicitly say when NOT to use it or list alternatives (e.g., set_keyword_target_url for URL-only updates, bulk_update_keywords for multiple), but the primary context is clear.

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