native_document_identity_initialize

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

Annotations provide only readOnlyHint=false, so the description carries the load and does so: it declares the persistent dictionary write, the fingerprint advance, and a hard refusal condition on non-empty drawings. That is exactly the mutation/blast-radius context an agent needs before calling a write tool.

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?

Three sentences, each doing distinct work: the action, the side effects, and the disambiguation/precondition. No repetition and no filler.

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?

Output schema exists, so return values need no explanation, and the description still covers side effects and refusal behavior. It does not address re-entrancy (what happens if invoked twice on an already-initialized drawing beyond the refusal) or whether the write can be undone, which would round it out.

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?

Zero parameters, so the schema is trivially complete and the description has nothing to add on inputs. Per the zero-param baseline this would be a 4, but the description mentions return values ('verified document PID and semantic fingerprint') rather than any parameter meaning, offering no input-side value.

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?

Names a specific verb ('initialize') and resource ('provider-owned persistent document lineage') and states the return ('document PID and semantic fingerprint'). The heavy jargon ('semantic fingerprint', 'native tracking') slightly obscures the plain intent, but an agent can still distinguish it from native_integrity_status, which reads status rather than bootstrapping it.

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?

Explicitly conditions use: 'Use once on an empty drawing to bootstrap native tracking; refuses non-empty drawings' — giving both the when and the when-not. It stops short of naming an alternative tool to consult first, which keeps it from a 5.

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