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

Beyond the readOnly/openWorld annotations, it discloses real operational behavior: it waits up to 25 seconds while an edit is still processing, includes previews for ready items, and notes that results are paged (5 vs 10 per page depending on mode). The 25-second blocking wait is exactly the kind of latency detail an agent needs before calling. It omits failure behavior when the wait expires and references an output field (`next`) that is undocumented anywhere.

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?

One dense run-on built from colons and dangling clauses, with the most common no-parameter case buried in the middle rather than front-loaded. The trailing example fragment ('an old print to restore, clothes to try on, something to add') adds no retrievable instruction. Content is present but structure actively impedes comprehension.

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 read-only, three-mode paginated list tool with no output schema, the description covers modes, page sizes, and polling latency, which is the right scope. It falls short by referencing a `next` field from the response that has no schema support, and by not saying what happens when the 25-second wait lapses. Annotations already cover the safety profile, so those gaps are the remaining ones.

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 0%, so the description must carry all three parameters, and it does attempt to: `ids` for up to 10 specific photos, `before` as the cursor taken from the response's `next`, and `uploads` for My photos plus derived images. The coverage is broad but the phrasing is fragmented enough ('pass the answer's next as before for the five after') that an agent could misread the pagination contract, and it never clarifies what `before` actually identifies.

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 never states a clean verb+resource; it opens with 'With ids, those photos (up to 10)' and describes outputs rather than the action, relying on the title for the 'list' framing. Three distinct modes (by ids, latest shoots, uploads) are discernible, but only after the agent parses a convoluted run-on. An agent can eventually tell it apart from siblings, but not quickly.

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?

Mode selection is genuinely specified: pass `ids` to retrieve specific photos and poll an edit's result, omit everything for latest shoots, and set `uploads: true` for My photos. However, no sibling tools are named (get_shoot, upload_status, edit are plausible alternatives), and there is no explicit 'do not use this when…' guidance, so the routing is implied rather than stated.

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