watch_runsRead a watch's run history (newest first), paged. Each run includes changed, diffScore, and signed before/after/overlay image URLs. Returns { items, nextCursor }.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The watch ID (UUID). | |
| limit | No | Page size (1–100). | |
| cursor | No | Pagination cursor from a previous nextCursor. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read operation. The description adds substantial context beyond the annotations: it specifies that runs are ordered newest-first, paged, and details the content of each run (changed, diffScore, signed image URLs) plus the response structure { items, nextCursor }. This provides a clear picture of behavior without contradicting the annotations.
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 description is three sentences, front-loaded with the core purpose, and includes only relevant details about content and response shape. No word is wasted.
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 paginated list tool with no output schema, the description covers the essential return structure and element fields. It specifies ordering, paging, and the cursor mechanism. Given the richness of annotations and schema, this is complete.
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?
The input schema documents all three parameters (id, limit, cursor) with descriptions, achieving 100% coverage. The description references pagination via the nextCursor return but does not add new meaning to the parameters beyond what the schema already provides. Thus the baseline of 3 for high schema coverage is appropriate.
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 uses the specific verb 'Read' to identify the operation, clearly specifies the resource as 'a watch's run history', and includes ordering and paging behavior. It distinguishes from siblings like watch_list (which likely lists watches) and watch_get (which gets a single watch) by focusing on run history.
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?
The description does not explicitly state when to use this tool vs alternatives, nor provide any exclusions or alternative tool references. However, the function is clear from the description and sibling tool names, making usage context implied. There is no explicit guidance for selecting between watch_run, watch_get, and watch_runs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose with explicit 'use when' and 'do NOT use' guidance in descriptions. The rendering tools are differentiated by output type (screenshot/PDF, hosted URL, branded artifact, extracted text), and the watch tools follow a patterned CRUD/run/test structure, leaving no ambiguity.
Most tools follow a 'prefix_verb' or 'prefix_verb_noun' pattern (e.g., rendex_screenshot, watch_create), but there are minor inconsistencies: 'render_artifact' lacks the 'rendex_' prefix, and 'watch_runs' is a noun rather than a verb. Overall, the names are still predictable and readable.
With 13 tools, the server is well-scoped. It covers two domains—rendering (5 tools) and monitoring (8 tools)—without unnecessary overlap or excessive complexity. Each tool earns its place in the set.
The rendering side covers screenshots, PDFs, hosted URLs, branded artifacts, and content extraction. The watch side provides full lifecycle management (create, get, list, update, delete), plus immediate runs, run history, and testing. There are no obvious gaps or dead ends in user workflows.