canvas_connector_version

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, so safety is covered structurally. The description adds genuinely new behavior: it compares the installed version against the npm registry and returns an update command. There is mild tension with openWorldHint=false since an npm registry lookup is an external call, but the operation is deterministic and read-only, so it is not a true contradiction.

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 core question ('Which version... is running'), then the mechanism, then the usage cue and exclusion. Nothing is padding; the slightly compressed 'checked against npm, where it is published' phrasing still reads 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?

No output schema exists, so the description carries the return-value burden and does: installed version, newer-version availability, npm as the source of truth, and the update command. With zero parameters and clear annotations, nothing an agent needs in order to call this 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?

The tool takes zero parameters and the schema is correspondingly empty, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly implies no input is needed by describing the check as fully self-contained.

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: reports which version of the Neuro-CanvasLMS connector is running, whether a newer one exists, where it is published (npm), and the update command. It also explicitly scopes itself out of the Canvas data domain with 'Does not read Canvas,' which cleanly separates it from the ~60 sibling canvas_* tools that all read Canvas content.

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?

Gives an explicit trigger: 'Use it when the user asks whether the connector itself has an update.' Combined with the 'Does not read Canvas' exclusion, an agent can tell this apart from every sibling. It stops short of naming a fallback tool, but no sibling covers connector versioning, so there is nothing to route to.

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