novelai_metadata

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

Goes well beyond the annotations (readOnly/idempotent/non-destructive) by disclosing the exact metadata sources read (PNG text, alpha-channel stealth, EXIF), that it is purely local with no token/network/credit cost, that it never alters the image, and that metadata text is data not instructions with missing fields left unguessed. This is unusually rich behavioral context, including a prompt-injection guard.

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?

Front-loads the purpose, then layers sources, return values, and safety constraints with zero filler. Every sentence carries distinct information (sources, return fields, cost/auth profile, immutability, injection caveat).

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?

With no output schema, the description still enumerates return values (prompts, seed, model, saved parameters, optional raw metadata), and annotations already carry the safety profile. An agent has everything needed to select and invoke 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 50%: path and run_id are documented in the schema, and the description reinforces them via 'local image or prior output' and 'optional raw metadata' (include_raw). The image_index parameter is undocumented in both the schema and the description, so the description only partially compensates for the coverage gap.

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?

States a specific verb ('Extract') and resource ('embedded NovelAI generation metadata') plus the two input sources (local image or prior output). This is clearly distinguishable from siblings like novelai_view_image or novelai_history, which do not extract metadata.

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?

Establishes clear context: reading metadata from a local image path or a saved generation ID, which maps to the path/run_id alternatives. It does not, however, explicitly contrast itself with sibling tools such as novelai_history or novelai_view_image, so the routing guidance is implied rather than stated.

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