Upload an image (이미지 업로드)

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

Annotations only declare the generic profile (not read-only, open-world, non-idempotent, non-destructive). The description adds genuinely non-inferable behavior: uploads are ephemeral and reference-counted via 'attachment_ref', becoming invalid in ~15 days if unreferenced, and the returned URL is not directly usable in post bodies. That is exactly the kind of lifecycle detail structured fields cannot carry.

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, front-loaded with what is returned, then the placement rule, then the retention caveat and the prohibition. Nothing is padded. Minor friction from the code-fenced identifiers and the stray line breaks in the source, but the information density is high.

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?

An output schema exists, yet the description still highlights the two return fields that carry workflow semantics, which is the right call for a tool whose outputs must be threaded into a later call. Combined with the fully documented 5-parameter schema and the retention warning, an agent has everything needed to call it and use the result correctly.

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 100%, so the schema already documents blog_url, file_path, style, width, and height including defaults and size limits. The description adds nothing about input parameters — the identifiers it discusses ('substitution', 'attachment_ref') are return values, not inputs. Baseline 3 is appropriate.

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 description names a specific verb+resource ('Upload an image') and immediately states the two artifacts it returns ('substitution' and 'attachment_ref'). That distinguishes it unambiguously from every sibling, none of which deal with binary media, and it tells the agent the tool is a prerequisite step for publish/update rather than a terminal action.

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?

It gives explicit, actionable when-and-how guidance: put 'substitution' verbatim in the body, pass 'attachment_ref' in attachments 'when publishing/updating', and a clear negative instruction — 'Do not put the returned URL into the body directly.' It also supplies the consequence of skipping the step (garbage-collection after ~15 days), which makes the correct usage path obvious.

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