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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the agent knows this mutates state. The description adds the build_id return and the gate follow-up, which the annotations do not convey. However, it never explains the destructive side — e.g. that mark_baseline=true may overwrite an existing baseline — which is the most important behavioral caveat for a tool flagged destructive.

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, correctly front-loaded with the core action and the highest-value caveat (server-side fetch vs client filesystem). Slight redundancy: the 'fetched server-side' note repeats the schema's 'Works in hosted mode'.

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 correctly discloses the return value (build_id) and the next step, so an agent can chain into the gate query. The only gap is behavioral — what marking a baseline displaces — which a destructive-flagged mutation tool should mention.

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 every parameter, including the stdio-vs-hosted constraint and the 'no extension added' rule for screenshot_name. The description largely restates this, adding only the minor tie between mark_baseline and later screenshot_name binding. Baseline 3 applies 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 ('Upload screenshots to a SmartUI project as a new build') and covers both ingestion modes, file_paths and source_urls. This distinguishes it cleanly from siblings like smartui_screenshot_review and smartui_build_query, which operate on existing builds.

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 conditional guidance: file_paths only works over local stdio, source_urls for hosted mode, project_id for token auto-resolution, mark_baseline to seed a baseline. It also names the follow-up tool (smartui_build_query(action=gate)). It stops short of saying when to use this vs smartui_baseline_manage for baseline operations.

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