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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: no pagination, the full list is returned in one response, and profiles change infrequently because they are set at account setup. It also discloses the region precedence rule (the account-registered region always overrides the region argument, fixed per account) which is not in the annotations or schema. The only missed item is return ordering/edge behavior when zero profiles exist.

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?

Front-loaded with the verb and resource, then structured return fields, a bulleted use-case list, a frequency/response note, and a region block — easy to scan. It is somewhat long and the region section duplicates schema text, costing a point, but every other sentence carries actionable information.

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 parameterless read-only list tool with no output schema, the description supplies the return shape (the profile fields), response sizing (all rows, no pagination), why the tool exists, and the region caveat. An agent has everything needed to decide to call it and to interpret the result without opening anything else.

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% and both parameters carry enums with descriptions, so the schema does the heavy lifting. The description's region paragraph largely restates the schema's guidance (default kr, ask the user when ambiguous, see kollus://guidance/regions) and adds only the account-region precedence note, while the order parameter is never mentioned in the description at all. 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?

Opens with a specific verb+resource: listing encoding/transcoding profiles registered to the service account, and pins the underlying endpoint (GET /media-profiles). It also enumerates the profile fields returned (container_format, video_codec, bitrate, resolution, is_default_preset, etc.), so an agent knows exactly what this resource is and can distinguish it from siblings like list_media_contents or get_content_detail.

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?

Gives two explicit use cases: resolving profile_key required by the pass-through upload API, and auditing account-level profile settings for quality debugging. It also states a negative boundary — that which profile was applied to a specific video cannot be determined here or in get_content_detail — which prevents a plausible misfire. Region selection guidance is included with the instruction to ask the user when ambiguous.

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