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

Goes well beyond the destructiveHint=true annotation: it discloses omission-vs-null semantics per field, that at least one effective edit is required, refusal behaviors (site_archived, brand fields refused), validation constraints on focalEntityId, and that no scan is launched or history rewritten.

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-loads the core purpose and every sentence carries real semantic content, but the density is high and a few clauses (e.g. the site-field compatibility remark) could be tightened without loss.

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?

Despite an output schema existing, the description still orients the agent on the return shape (site metadata plus scanConfig with context, focus, tracked entities and config) and covers refusals and invariants, leaving nothing needed to call it correctly.

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?

With only 29% schema description coverage, the description compensates thoroughly: it explains preservation vs clearing for description, focalEntityId, strategicGoal and models, the replace semantics of topicProfile, and the plan check for model edits.

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 ('Edit one research Topic by topicId from list_sites_and_topics') and anchors the entity source, so it is clearly distinguishable from create_topic, get_topic and archive_topic.

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?

Gives explicit prerequisites ('Read get_topic and get_scan_config first'), states the alternative for the retirement case ('use archive_topic for retirement'), and clarifies that model edits don't launch a scan. When/when-not and alternatives are all present.

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