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

Beyond the destructiveHint/readOnlyHint annotations, the description adds real context: the change is not saved, the person can undo it and saves manually, and the document is validated first and refused with problems. It also notes the auth requirement ('Needs an MCP key that can edit'), which annotations do not cover.

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 short sentences, each earning its place: the action, the persistence/undo behavior, and validation/auth. The most decision-relevant facts (NOT saved) are front-loaded and capitalized.

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 nested-object mutation with no output schema, the description covers validation failure, non-persistence, and auth prerequisites well. Minor gaps remain around the note parameter and the return value on refusal, but nothing critical to correct invocation 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 100%, so the schema already documents doc, note, and pairing_id. The description reinforces that doc is validated and complete but adds no syntax or format detail for the note or pairing_id parameters beyond the schema. Baseline 3 applies.

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 gives a specific verb+resource ('Replaces the document in the person's open editor') and distinguishes this from the get/read/save siblings by scoping it to the live editor canvas. An agent can route between editor_set_doc, editor_get_doc, and save_onboarding_doc 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?

The description makes clear this is for pushing a document into the person's open session rather than persisting it, and it says the change is visible and undoable. It stops short of explicitly naming alternatives like save_* or validate_* and when to prefer them.

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