production.facial_inspect

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

The description adds genuine context — the facial plan.json is immutable and the body Action is never modified — which explains blast radius. However, 'Candidates are new Actions evaluated through NLA tracks' and the presence of an `apply` switch imply state creation that conflicts with the declared readOnlyHint=true, and prerequisites such as TIMING_INPUT_REQUIRED for speech are stated without explanation.

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 text begins by repeating the tool name and a codename, then packs several unrelated rules into semicolon-joined fragments, so the key statement of purpose is never front-loaded. It is short but cryptically dense rather than efficient.

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 and annotations exist, so return values and safety hints need not be restated, but for a zero-required-parameter tool with 0% schema coverage the description leaves most inputs and the core operation undefined. Key constraints (TIMING_INPUT_REQUIRED, plan-first sequencing) are mentioned but not tied to specific parameters.

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 six parameters, so the description must carry the load. It only clarifies two of them (`apply` defaults false; `facial` is the immutable plan.json reference) and leaves brief, intent, options, and object_name entirely uninterpreted.

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 opens with 'facial_inspect: M7 facial unit', which restates the name plus an unexplained internal codename, then shifts to procedural rules rather than stating what the tool inspects or returns. It never says how it differs from the many adjacent facial_analyze_*, facial_review, or facial_compatibility_report siblings, so an agent cannot tell its job apart from theirs.

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' gives real workflow guidance, and 'Technical QA and artistic review stay separate' implies a division of labor. But no alternative sibling is ever named, and there are no explicit when-not-to-use conditions despite dozens of closel related facial tools.

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