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

Annotations declare the safety profile (idempotentHint=true, destructiveHint=false, readOnlyHint=false), and the description adds rich behavior beyond that: variant preservation rules, refusal-instead-of-silent-change, conflict-without-mutation semantics, no-op/no-duplicate-event on exact retry, and converted-thing handling. These are precisely the behaviors annotations cannot express.

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 core action is front-loaded in the first sentence, and each subsequent sentence carries a distinct behavioral rule (refusal, conflict, no-op, converted things). It is dense and long, but nearly every clause earns its place for a mutation tool with many edge cases; minor tightening is possible.

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?

Given a mutation tool with no output schema, the description is complete: it covers preconditions, conflict/refusal/no-op outcomes, and explicitly states the return value ('the same public thing read as look with thing_id'). Nothing an agent needs to call it correctly is missing.

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 50%: drawing_variant_name is documented in the schema, but thing_id is not. The description compensates by explaining the variant parameter's operational use (null deliberately selects the base; a string must be an exact variant offered by the new revision) and the retry patterns, adding meaning beyond the schema.

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 and resource: 'adopt a typed active thing's latest kind revision' with the owner role. This clearly distinguishes it from siblings like revise_kind (edits a kind) and thing_edit (edits a thing), so an agent can tell them apart without opening schemas.

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?

Extensive when/when-not guidance: untyped things have no revision to upgrade, a thing with an open sale offer cannot be upgraded, conflicts must be retried against the committed latest revision, and it routes to front_door when lost. This is explicit about preconditions and edge-case routing.

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