retry_asset_stage

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

With no annotations, the description carries the full burden of behavioral disclosure. It does add one genuinely useful fact — that successful other assets are retained — but says nothing about whether the retried stage's prior output is discarded, whether the operation is idempotent, what preconditions must hold, or what it returns. 'Rewind its cause' asserts a second behavior mode without explaining it.

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?

It is a single front-loaded sentence with no filler, which is structurally sound. But the economy is achieved by omitting substance rather than by compressing it — the phrase 'rewind its cause' is compressed to the point of being unparseable.

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?

This is a state-mutating retry operation with no annotations, no output schema, five required parameters, and a nested free-form object. Against that complexity, one sentence stating retention semantics is far short of what an agent needs to invoke it correctly or predict its effect.

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?

Five required parameters with 0% schema description coverage, including a free-form nested 'changes' object with additionalProperties, and the description explains none of them. It never clarifies what belongs in 'changes', what 'repair_note' is for, or how 'batch_id'/'asset_id'/'stage' interact, so the agent gets no compensating meaning from the prose.

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 verb 'resubmit' and the object 'an agent-repaired stage' give a rough sense of the operation, and 'retaining successful other assets' hints at partial-retry scope. However, 'rewind its cause' is opaque, and the definition never distinguishes itself from plausible siblings such as create_shape_repair_attempt, submit_shape_repair_candidate, or resume_generation. An agent would need to open the schema and guess.

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 implied condition 'agent-repaired' suggests a usage context; there is no explicit when-to-use, when-not-to-use, or alternative named among the eighteen siblings. Given the dense cluster of repair/retry/resume tools, this is a meaningful gap that leaves routing ambiguous.

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