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

Annotations declare readOnlyHint/idempotentHint/openWorldHint, but they do not capture the non-obvious side effect: this tool registers a photo with Unsplash as part of the search. The description surfaces that registration and explains the resulting id is immediately usable, which is exactly the kind of context annotations can't convey. It stops short of explaining what registration entails or any rate/auth concerns.

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?

A single front-loaded sentence that leads with the action and then qualifies the output usage; the parenthetical field references are dense but earned. Slightly overloaded sentence, but 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?

With no output schema, the description should characterize what comes back. It implies the top result gets registered and that ids feed `create_or_update_page`, but says nothing about whether the response is a list of photos, ids, URLs, or thumbnails, or how paging interacts with results. Adequate but leaves a real gap for a tool an agent must chain into page creation.

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 `page`, `query`, and `pick_first` are already documented, and the description adds cross-tool meaning for the registered photo id. However, "optionally register a chosen photo ID" reads as an opt-in manual choice, while the schema says `pick_first` defaults to true and auto-registers the top hit — a discrepancy that could mislead an agent about default behavior.

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?

States a specific verb and resource ("Search Unsplash photos via Wordy Page") and ties the result to a concrete downstream use (`photo` / `sections[].photo` in `create_or_update_page`), which clearly separates it from the page-management siblings. The secondary clause about "optionally register a chosen photo ID" is slightly fuzzy about who chooses, but the core action is unmistakable.

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 clear context for when to reach for this tool — sourcing a page header image — and names the consuming tool and the "one image per page" constraint. It does not state exclusions or alternatives, but no sibling tool performs photo search, so the routing value is still strong.

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