production.facial_compatibility_report

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

Adds real behavior beyond the annotations: apply defaults to false so this is a dry-run by default, facial is an immutable plan.json reference, candidates are new Actions evaluated through NLA tracks and the body Action is never modified, and speech without explicit timed phonemes fails with TIMING_INPUT_REQUIRED. This clarifies the mutation surface and error condition beyond readOnly=false/destructive=false.

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?

Leads with a redundant name echo plus undefined shorthand ('M7', 'NLA') instead of a plain purpose statement, and then dumps several distinct concerns (mapping policy, plan/apply, candidate mechanism, speech preconditions, QA separation) into one dense block with no structure.

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?

Although an output schema exists and return values needn't be described, the definition still leaves the core question unanswered: what compatibility is being measured and against what inputs. For a 6-parameter, zero-coverage compatibility report with a large sibling set, this is not enough to invoke confidently.

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 6 parameters, so the description must carry the burden. It only explains two of them (apply's default/dry-run semantics and facial as the immutable plan.json reference) and says nothing about brief, intent, options, or object_name.

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 by restating the name and adding opaque jargon ('facial_compatibility_report: M7 facial unit', 'Evidence-based semantic mapping (never names only)'). It never plainly states that this tool reports whether the facial rig is compatible for generating the intended expressions/speech. An agent must infer the verb ('report') and the resource ('facial rig compatibility') from the tool name alone.

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' and the TIMING_INPUT_REQUIRED precondition give some workflow context, but there is no guidance on when to choose this over the many facial siblings (facial_inspect, facial_classify_rig, facial_validate_lipsync, facial_review). 'Technical QA and artistic review stay separate' implies a boundary with facial_review but never names it.

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