changes_since

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

With no annotations the description carries the full burden. It usefully notes it reads 'real PR activity' and compares against a 'last saved review' (implying a prior review must exist), but it never states whether the operation is read-only, what permissions or tenant scoping is needed, or how results are produced.

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?

The comparison and its output list are front-loaded, followed by a compact use-case clause. It is appropriately sized with no wasted sentences, though the first sentence is dense.

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, and the description does cover the main return content, which helps. However, it omits the 'tenant' parameter entirely and doesn't clarify the dependency on an existing saved review, leaving gaps for correct invocation.

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 0% for the single 'tenant' parameter and the description never mentions it, offering no meaning, format, or default explanation. For a tool whose only parameter is undocumented in both schema and prose, the description fails to compensate.

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 (compare) and resources (the graph now vs. the last saved review) and enumerates the concrete outputs: safer/riskier modules, top holder change, pairing-task progress. It is clear what the tool does, though it does not explicitly distinguish itself from the adjacent succession_review sibling.

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 explicit trigger phrases ('what changed since last time', 'did the plan work') that map an intent to this tool. There are no when-not conditions or named alternatives, but the usage context is unambiguous.

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