production.character_modeling_audit

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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so safety needs no restating. The description does add genuine expectation-setting: each finding carries type, region, severity, evidence and suggested_action, and there is deliberately no aggregate score – that prevents an agent from looking for a single verdict. It says nothing about cost, whether all six passes always run, or how the optional intersections pass affects findings.

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?

A single dense sentence, front-loaded with the output shape and then the covered domains, with zero filler. It loses a point only because it spends its lead on return fields (already in the output schema) rather than on the verb and target.

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, yet the description spends most of its length restating them. What is actually missing is the operational context: what object_name refers to, what profile/manifest select, and whether region definitions must exist first. For a four-parameter aggregate audit at 0% schema coverage, this is not enough to call 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 description coverage is 0% across four parameters, so the description carries the full burden. It only implicitly gestures at include_intersections by listing intersections among the checks; profile (default HUMANOID, presumably selects the proportion ruleset), manifest, and object_name are left entirely unexplained – notably what profile values exist and what a manifest supplies.

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 names the resource domain (character modeling) and enumerates the six check families covered – surface, asymmetry, proportions, intersections, topology, weights – which maps onto the sibling analyze_* tools and signals this is an aggregate audit. It never states the verb explicitly ('audit a character model') and never names the target object, so the agent infers purpose from the name plus the field list.

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?

There is no statement of when to call this versus the narrower siblings like character_analyze_surface or character_analyze_intersections, and no prerequisites (required regions, locked regions, evaluation state). 'No overall quality score' hints at scope but does not route the agent between this and alternatives.

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