ax_activate

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

With no annotations, the description carries the full burden and does so: it discloses generation-safe fail-closed behavior, the provider-specific routing rules (paired-page vs native), that DOM errors never use native/coordinate fallback, the fallback chain, and the route values returned. This is unusually rich behavioral context.

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?

Dense but front-loaded: the core action and its scoping constraint lead, followed by safety and routing details. Every sentence carries information, though the density is high and slightly demanding, keeping it just below ideal concision.

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 no output schema, the description explains the result format (route=chrome_extension|ax|uia|web_dom|element_center) and the post-call requirement to rerun ax_read. For a tool this complex, the agent has everything needed to invoke 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?

Schema coverage is 100%, so the schema already documents all three parameters including the background fallback-only note. The description reinforces that snapshot_id is ephemeral/immediately-preceding and node_id must be actionable, but adds little beyond the schema's own descriptions.

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+resource ('Activate one actionable node from the immediately preceding ax_read') and scopes it with the required snapshot_id and node_id. It is clearly distinguishable from siblings like ax_click and chrome_activate, which do not have the generation-safety constraint.

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 clear context: activation must follow an immediately preceding ax_read, and the agent must 'rerun ax_read after any result' because an accepted token consumes the generation. It does not explicitly contrast with ax_click or ax_focus (click vs activate), so it falls short of full when/when-not guidance.

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