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

With annotations already declaring idempotency, non-destructiveness, and open-world scope, the description still adds real behavioral content: revisions are immutable, omitted fields are retained, arrays and conditions replace their whole field, assessment null clears the assessment, and prior revisions remain readable. It stops short of describing the response payload or error shapes beyond the permission/token requirements.

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?

Four dense sentences, front-loaded with the core mutation semantics before prerequisites. Every sentence carries information, though the first sentence is long and could be split for faster scanning.

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 14-parameter mutation tool with nested objects and no output schema, the description covers authorization, concurrency (expected_revision), idempotency, field-replacement rules, and non-destructive retention. It omits any hint of the returned revision/structure, which matters slightly more here because no output schema exists.

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 only 57%, and the description compensates well: the anyOf 'at least one editable field' contract, the retain-on-omit rule, whole-field array/conditions replacement, and assessment-null-clears semantics are all extra meaning not encoded in the schema. It leaves several parameters (relationship targets, sources, stored_artifacts titles) to the schema, which is acceptable given their inline descriptions.

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 ('creates a new immutable revision') plus an actor constraint ('the original author'), which is far more precise than the bare tool name. It implies but never explicitly contrasts with the sibling publish_contribution, so an agent must infer the revise-vs-publish distinction from the name alone.

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?

Provides clear operational context: the caller must be the original author, must hold current Orbit write permission and a contributor bearer token, and must supply an expected_revision plus at least one editable field. It does not name alternatives (publish_contribution) or state when revision is inappropriate versus publishing a new contribution.

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