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

Annotations already declare the mutation/safety profile (readOnly=false, destructive=false, idempotent=false), so the bar is lower. The description adds valuable context beyond that: only the image is regenerated and the caption is preserved exactly, including user edits made while waiting. It omits permissions and result format, but the preservation guarantee is genuinely useful.

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 tight sentences, front-loaded with the action and its precondition, with no filler. Every clause earns its place.

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 single-parameter mutation with no output schema, the description covers the trigger condition and the non-destructive scope (caption untouched). It stops short of noting what the caller gets back or how to confirm success, but nothing essential to correct invocation is missing.

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 postId is fully documented as 'the post whose image should be made again'. The description adds no format, range, or sourcing detail beyond the schema, so the baseline 3 applies.

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 (remake the image) and resource (a post's image), and distinguishes itself from siblings like get_generation_status by explaining what 'retry' concretely means. An agent can tell this apart from change_image or add_image_to_post without opening schemas.

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?

Clearly states the triggering condition: a post that has a caption but never got a picture, signaled by get_generation_status reporting image_failed or imageStatus 'failed'. It names the read sibling that surfaces the precondition, though it doesn't explicitly contrast against alternative image tools (e.g. change_image) for the case where the user wants a different image.

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