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

Annotations already declare readOnlyHint=false, destructiveHint=false, so the baseline is covered; the description adds real value beyond them by disclosing the blast radius (all unsaved changes are captured, not just one item), the human-in-the-loop convention, and a specific refusal condition tied to site origin. It omits what happens on success (e.g. whether a checkpoint id is returned) and any permission 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?

Three short sentences, front-loaded with the effect and immediately followed by the gating condition; no filler. The colon-spliced second sentence is a bit compressed but still parses cleanly.

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 two-parameter mutation with no output schema, the description covers purpose, timing, and a refusal rule, which is most of what an agent needs. The remaining gap is the required "message" argument, whose meaning must be guessed, plus any note on what a successful save yields.

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 50%: projectId is documented as "Project id from list_projects," but the required "message" parameter (1-120 chars) has no description anywhere. The description never mentions either parameter, so an agent gets no help inferring that "message" is the checkpoint label or what it should contain.

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?

"Saves all unsaved changes as a restore point" names a specific verb (saves) and a specific resource/effect (restore point over unsaved changes), which separates it from list_checkpoints and restore_checkpoint without ambiguity. It stops short of naming either sibling explicitly, so the contrast is inferred rather than stated.

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?

It gives an explicit when: "Only when the user asks you to save," and an explicit when-not: normally the user reviews and saves in Xodia themselves. It also states a hard precondition for refusal (live branch of a GitHub-imported site). It does not point to restore_checkpoint or list_checkpoints as follow-up alternatives, 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.