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

The description adds real context beyond the annotations: the return is markdown with the photographer's credit, and Unsplash-hosted photos are served externally rather than through upload_media (consistent with openWorldHint=true). However, annotations declare readOnlyHint=false and idempotentHint=false, implying a persistent side effect, and the description never says what state is written or what happens if the same photo is used twice.

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?

The content is dense but structurally poor: the lead sentence "On one site of the account, named in site." is a dangling fragment that delays the actual purpose. The most decision-relevant fact, that this returns a markdown snippet rather than inserting anything, is buried mid-sentence.

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?

With no output schema, the description carries the burden of explaining the return value, and it does describe the markdown form and caption. It falls short on the mutation semantics implied by readOnlyHint=false and on the fate of the alt value when omitted, leaving meaningful gaps for a write-flagged tool.

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%, so the baseline is 3. The description restates that id comes from search_photos and that site scopes the account, but it never explains the optional alt parameter for this tool — alt only appears in the sentence about set_feature_image, which uses a different parameter set.

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 implies the tool turns a search_photos result into an embeddable markdown snippet ("Answers markdown: the photo with its photographer's credit as the caption"), but the core verb "use" is vague and the opening sentence is a fragment. The actual action is only inferable by reading to the end and combining it with "Paste it into create_post", so an agent must work to determine whether the tool inserts the photo or returns text.

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 explicitly routes the agent: use this for a body paragraph, use set_feature_image with url/alt/caption for a cover, and Unsplash photos bypass upload_media. It names the sibling alternatives and the consuming tools, though it never states a when-not-to-use case such as a photo already uploaded via upload_media.

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