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

Annotations declare readOnlyHint and openWorldHint, so safety is partly covered, but the description adds non-obvious behavioral facts: photos are hotlinked rather than copied, and the upload_asset call "stores nothing and reports the use to Unsplash." Those details cannot be inferred from the annotations. It does not describe the result object's structure in full, but names the key result fields (url, stock.downloadLocation, credit).

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?

Four sentences, each carrying distinct information (purpose, when to use, hotlinking workflow, credit requirement), and front-loaded. The middle sentence is long and packed with nested instructions, which slightly hurts readability, but nothing is repeated.

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?

Given there is no output schema, the description supplies enough about the return shape (url, stock.downloadLocation, credit fields) and the required follow-up to call the tool and use its results correctly. It never says how many results to expect or how pagination interacts with the credit workflow, which is a minor gap.

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 query, limit, offset and projectId are already documented in the schema. The description explains query intent ("a real-world photo") but adds nothing about limit, offset or projectId usage. A 3 baseline is appropriate when the schema does the heavy lifting.

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 plus the provider: "Search Unsplash for stock photos." That immediately separates it from generate_image and upload_image among the siblings, and the opening sentence front-loads the distinction between fetching real photos and generating them.

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?

Explicitly says when to use it ("when you need a real-world photo and the user has not supplied one"), which implicitly rules out generating one or reusing a supplied asset. It also prescribes the follow-up sequence — setting media.src to the returned url and calling upload_asset with sourceUrl/downloadLocation — so the agent knows the next step, not just when to start.

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