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

With annotations only declaring readOnlyHint=false and destructiveHint=false, the description adds real behavioral context: the prior failure refunded credits and this retry charges 2 again, plus that the result surfaces on a card. The instruction 'say so' usefully tells the agent to disclose the cost to the user, though the phrasing is terse.

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?

Four short sentences, front-loaded with the core action and cost consequence. The telegraphic 'say so' is efficient but borders on cryptic; otherwise there is no 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?

An output schema exists, so the description needn't explain return values, and it nonetheless covers cost, ownership, and result presentation. It omits what happens if the retry fails again, a minor but real gap for a retry tool.

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 description coverage is 100% with a single 'image' param already documented as 'the failed look id', so the baseline is 3. The description adds only the ownership constraint, not additional parameter semantics.

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 the action ('Try a failed look again') and the resource is identifiable from the tool name retry_image. It does not, however, explicitly distinguish itself from the sibling retry_clip and retry_video tools, and the term 'look' is used instead of 'image', which leaves the resource slightly ambiguous.

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?

'Only the user's own looks' gives a scoping constraint, which implies when the tool is applicable. But no alternatives (retry_clip, retry_video) or failure conditions are named, so the agent must infer the boundary conditions.

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