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

The description goes beyond annotations by revealing that the call shares the user's app page with Screen Browser, explicitly excludes credentials from evidence, and states that a reply comes on the run. It also clarifies side effects (nothing retried, guide unchanged). These are critical behavioral disclosures not covered by readOnlyHint/idempotentHint/destructiveHint. No contradiction.

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?

Three sentences with no filler. The core action is front-loaded, followed by scope limitations and a critical user-consent warning. Every sentence adds value, and the structure leads with the most important information.

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 privacy-sensitive mutation tool, the description covers purpose, usage conditions, side effects, data-sensitivity, and the response location. An output schema exists, so return format need not be described. Nothing essential is missing for an agent to call this safely and 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 description coverage is 100% and both parameters (run_id, note) are already well documented in the schema. The description does not add extra meaning about the parameters themselves; it focuses on the overall behavior. Baseline 3 is appropriate since the schema carries the parameter burden.

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 ('Send'), a precise resource ('a failed run's evidence'), and the destination ('to Screen Browser'). It also explicitly scopes what it is not (no retry, no guide change), distinguishing it from other run-related tools. Clear and unambiguous.

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 when-to-use ('Only for runs that failed on our side') and what it does not do (no retry, no guide change). Also adds a mandatory prerequisite ('Ask the user before calling') and a privacy caveat. It doesn't explicitly name alternative tools, but the schema for run_id references get_run, providing the needed context. Strong guidance.

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