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

Annotations declare destructiveHint=true and idempotentHint=false, and the description goes well past that: it names the resulting state ('the layout's own colours come back'), the protected resource (paid artwork), the required precondition (current expectedVersion), the failure mode and retry loop, and the cost ('Free'). That is substantive context an agent needs to act safely on a destructive call.

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?

Front-loads the trigger, then scope, then guardrails, then the retry rule, then cost — a sensible ordering. It is dense and slightly run-on in the middle clause, but every sentence carries information and none are filler.

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 destructive, version-guarded mutation with no output schema, the description covers trigger, scope, protected content, precondition, conflict recovery, and cost. It does not say what is returned or how the optional projectId/accountHandle/locale affect the operation, which is the remaining gap.

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 33%, so the description must compensate, and it does for the two decision-critical parameters: slideId means 'one slide' while omitting it means the whole deck, and expectedVersion carries conflict semantics with the DECK_CONFLICT failure path. The three ancillary params (locale, projectId, accountHandle) are not explained in the description, leaving some gap.

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 ('remove the drawn background... from one slide or from the whole deck') and explicitly names the sibling that created the artifact (antix_attach_deck_image). It also distinguishes itself from paid-artwork removal, so an agent can tell exactly what is and isn't in scope.

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 ('when the user asks to remove a background'), the two supported scopes, an exclusion ('never removes artwork that was paid for'), and a conflict-recovery procedure ('on DECK_CONFLICT, read the deck again and repeat the same intended change'). Nothing about when to reach for this tool is left to inference.

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