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

Annotations cover the safety profile (non-destructive, non-idempotent, closed-world), so the bar is lower. The description still adds real behavior: it pins original bytes, derives WebP/AVIF delivery sizes, and returns a full manifest entry, plus the explicit no-publish/no-paid-media boundary. It omits cost, duration, or whether re-running creates duplicate variants.

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?

Three tight sentences with the core action front-loaded, followed by result, reuse guidance, exclusions, and the one parameter hint. Dense but each sentence carries information; 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?

For a non-destructive mutation with annotations and no output schema, the description covers what is produced ('returns the full asset manifest entry') and what is not done. The main gap is the unexplained set of input parameters, which makes correct invocation harder than it should be.

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 0% across 6 parameters, and only 'panorama' is given meaning in the description. The five others (path, mediaId, workspaceId, worldId, storagePath) are left with names and formats only, so the description does not compensate for the coverage 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?

Specific verb (optimize/prepare) plus a precise resource (uploaded or completed generated workspace asset) scoped to a hosted world. It clearly distinguishes itself from siblings like create_asset, update_asset, or render_media by describing the optimize-and-derive-variants step.

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?

States exclusions explicitly ('Does not generate paid media or publish') and gives conditional parameter guidance ('Use panorama=true for 360-degree textures'). It also tells the agent what to do with the result ('Reuse this entry in site assets'). No sibling alternative is named, so it falls short of a 5.

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