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

Annotations already declare it as a non-destructive, non-idempotent, closed-world mutation, so the bar is lower; the description still adds substantive context the annotations cannot: no media generation, no credit charge, no library change, and it returns a new brief and quote rather than producing assets. The optimistic-concurrency requirement ('requires the current brief revision') is also disclosed. It stops short of saying what a 'replace' discards from the existing step.

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?

Five short sentences, action front-loaded, with the cost/side-effect disclaimer and the next-edit instruction at the end where they are most useful. It is dense but every sentence carries information; the only cost is a slightly telegraphic register ('the named brief flow') with no wasted prose.

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 6-required-parameter mutation with no output schema, the description does well on the return contract ('returns a new brief and quote') and the follow-up workflow ('read the returned recipe_key'), but leaves the two most semantically loaded parameters, factor and shot_index, entirely unexplained. An agent can call it correctly but cannot reason about the effect of a given factor value.

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?

With 50% schema description coverage, the description partially compensates: it explains look_keys defaulting to all looks on the flow, step_index as append-vs-replace, recipe_key as 'the named brief flow', and expected_brief_revision as the current revision. But factor (the numeric upscale multiplier, exclusiveMinimum 0) and shot_index (1-8) get no meaning at all, and 'Photo format is shared across the shoot' is too vague to resolve them.

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?

Specific verb and resource: 'Append or replace one image upscale' names the exact operation on the shoot plan, and 'Revises the selected looks using the named brief flow' scopes the affected entities. It is clearly distinct from plan_shoot_image / plan_shoot_edit / plan_shoot_video by naming the upscale operation, though it never explicitly contrasts itself with those siblings.

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?

'Requires the current brief revision' and 'Read the returned recipe_key before the next edit' give real pre/post conditions for chaining calls, and 'omit for every look using it' is echoed from look_keys. However, there is no statement of when to choose upscale over plan_shoot_edit or plan_shoot_image, and no explicit exclusion criteria; usage is implied by the operation name rather than guided.

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