brightspace_check_updates

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

The annotations already declare readOnlyHint=false and idempotentHint=false; the description adds the reason — the tool writes a snapshot file and later calls compare against it, so repeat runs are stateful and non-idempotent by design. That is genuine context beyond the annotations, though the state location and whether a snapshot can be reset or inspected remain unstated.

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?

Two short sentences with no filler, front-loaded with the primary action, and the supporting detail trails it.

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 four-parameter, stateless-looking tool with no output schema, the description explains the stateful baseline concept and the comparison result well enough to call it correctly. It could say more about where the snapshot lives or what happens on the first run, but the core mechanics are covered.

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 every parameter is already documented in the schema; the description only adds why includeFiles exists (hashing bytes). The baseline 3 applies because the schema does the heavy lifting and the description adds marginal meaning.

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 states a concrete verb pair (compare / create baseline) and a concrete resource pair (course content metadata vs. the tool's own snapshot), which is enough to distinguish it from the listing and reading siblings. It stops short of naming the alternative (e.g. fetch content directly) an agent should pick when it does not want drift detection, so it is clear but not fully differentiated.

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 a clear triggering condition — run this to detect changes since your last baseline — and a specific follow-up pattern (repeat calls share a snapshot). It does not state when a caller should prefer the read/list siblings, nor whether a first run must precede the comparison, which keeps it below a 5.

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