get_target_changes

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

With no annotations, the description carries the burden of behavioral disclosure. It reveals that results are ordered newest first and that limit is capped at 100 server-side, which is important behavioral context. However, it doesn't mention error behavior, pagination, or read-only semantics, but the 'get' verb implies safety. Overall, it adds meaningful value beyond the schema.

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 description is a single sentence that packs the essence: what, scope, ordering, and a server-side constraint. It is front-loaded with the core action and every phrase earns its place. No filler or repetition.

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?

The description covers the essential aspects needed for correct invocation: the meaning of changes, ordering, and the limit cap. It does not explain error handling or prerequisites, but given that an output schema exists (so return format is covered) and the tool is a simple read operation, the description is quite complete. A slightly fuller note on how to interpret the 'new/changed/removed' categories would push it to 5, but it's sufficient.

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 schema has 0% description coverage, so the description must compensate. It clarifies 'limit' with the cap note and implies its usage, but it does not explicitly explain 'target_id' beyond being an identifier (which is fairly self-evident from the name). It also describes the result content ('new/changed/removed findings'), which indirectly helps. Given the low coverage, this is adequate but not thorough.

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 clearly states the verb ('get'), the resource ('target changes'), and the exact nature of those changes ('new/changed/removed findings across scans'), plus the ordering ('newest first'). This distinguishes it from siblings like scan_get_findings (which presumably lists all findings) and get_target (which retrieves target details). It is unambiguous and specific.

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 implies when to use the tool (to see recent changes) but does not explicitly mention alternatives or exclude cases. It states 'across scans' to clarify scope but gives no guidance on when to prefer this over scan_get_findings or other listing tools. The context is clear, but explicit routing is missing.

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