ap_append_mesh

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

With no annotations, the description carries the behavioral burden and does it well: it discloses wire re-encoding, newline restoration, forbidden characters, the 8 KB cap, and path slash conversion. It stops short of discussing reversibility or failure modes, but the append operation is reasonably clear.

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 description is compact, front-loaded with purpose, then uses the remaining sentences for constraints and guidance. Every clause earns its place, and the wire-format constraints are grouped logically.

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 two-parameter additive tool with no required parameters and no output schema, this description is effectively complete. The agent knows what to provide, how to provide it, which option to prefer, and the hard constraints that could cause failures.

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 coverage is 100%, but the description adds substantial meaning beyond the schema: mutual exclusivity of 'path' and 'obj_data', the preference rule, inline OBJ character restrictions, the 8 KB limit, and newline handling. This is far beyond the baseline.

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 a precise verb and resource: 'Append geometry to the current project', then specifies the two allowed input sources. This makes the tool distinct from export/import siblings and clearly communicates what it does.

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?

The description gives strong within-tool guidance: exactly one of 'path' or 'obj_data' must be supplied, and 'path' should be preferred for anything non-trivial. It does not explicitly contrast this tool with ap_import_asset, but the usage context is clear enough.

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