production.facial_coordinate_gaze

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses real behavioral traits: default apply=false plan mode, facial as an immutable plan.json reference, that candidates are new Actions evaluated via NLA tracks, and that the body Action is never modified. It also names a concrete error condition (TIMING_INPUT_REQUIRED for speech without timed phonemes/visemes), though that speech clause looks like boilerplate for a gaze tool.

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?

The premium front position is wasted on repeating the tool name followed by an opaque unit code ("M7 facial unit") instead of a purpose statement. The semicolon-chained clauses mix behavioral rules, error conditions, and an irrelevant speech caveat with no clear hierarchy.

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?

An output schema exists, so return values need no explanation, but for a 7-parameter tool with 0% schema coverage the description leaves most inputs unexplained and never disambiguates this tool from the overlapping gaze/saccade generation siblings. It is not complete enough for reliable selection or invocation.

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 0% across 7 parameters, so the description must carry the full semantic burden, yet it only sheds light on two: apply (default false) and facial (immutable plan.json reference). brief, intent, options, object_name, and operation_id are left completely undefined in both schema and prose, which is a large gap for a low-coverage schema.

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 restates the tool name and adds opaque internal jargon ("M7 facial unit", "Evidence-based semantic mapping (never names only)") without ever stating in plain terms what the tool does — coordinate gaze targets? plan gaze? The siblings facial_generate_gaze and facial_generate_saccades overlap heavily and are never distinguished, so an agent cannot tell which to pick from this text.

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?

"plan first, apply=false by default" implies a dry-run-then-commit workflow, and the TIMING_INPUT_REQUIRED clause flags a conditional failure mode. But there is no explicit when-to-use vs when-not guidance and no routing to the many facial_generate_*/facial_plan_* alternatives, so the workflow is only implied.

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