watch_my_form_responsesReturn any existing individual answers immediately, or wait briefly until the respondent saves their next answer, even while the form remains in progress.
| Name | Required | Description | Default |
|---|---|---|---|
| askId | Yes | ||
| since | No | Optional ISO timestamp cursor. | |
| timeoutMs | No | Maximum wait in milliseconds, capped at 120000. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds meaningful behavioral detail: it returns existing answers immediately, waits for the next save, and works even while the form is in progress. This goes beyond the annotation hints and clarifies the true watch semantics.
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 a single concise sentence that front-loads the primary behavior ('Return any existing individual answers immediately') and packs the waiting behavior and in-progress nuance without fluff. Every phrase earns its place.
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 the tool has 3 parameters, no output schema, and strong annotations, the description sufficiently outlines the core behavior and fits with the schema's timeoutMs and since parameters. It doesn't cover timeout edge cases or response format, but that is not critical given the structured schema and safety annotations.
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 67% with only askId lacking a description. The description does not explicitly explain askId, but the overall behavior implies it refers to the form/ask identifier. It adds no direct parameter-level meaning beyond what the schema already provides, so the baseline score 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 clearly states what the tool does: returns existing individual answers immediately or waits for the next answer from the respondent, even on an in-progress form. This distinguishes it from simple retrieval tools like get_my_form_responses or get_responses by emphasizing the watch/wait behavior.
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 gives clear context for when to use it (when you want existing answers immediately or need to wait for the next one) but does not explicitly state when not to use it or name alternative tools. The sibling names imply alternatives, but the description itself lacks an explicit contrast.
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.
There is clear overlap between several tools: create_ask is explicitly a backward-compatible alias for create_form, making them nearly indistinguishable. get_my_form_responses vs get_responses and watch_my_form_responses vs watch_ask also serve similar purposes with only subtle differences (form ownership vs generic ask). The creation session tools (join_creation_session, update_creation_session) and creation tools (create_form, create_feedback_form) have moderately clear boundaries but could confuse agents about when to use session tools vs direct creation.
The naming mostly follows a verb_noun pattern (create_form, list_asks, watch_ask) and many share a consistent 'my_' prefix for owned resources. However, the aliasing (create_ask), the distinction between 'ask' and 'form' terminology, and create_feedback_form vs create_form introduce inconsistency in domain vocabulary. Watch_ask vs watch_my_form_responses and get_responses vs get_my_form_responses use parallel but not fully consistent naming.
11 tools is a reasonable count for a form lifecycle server. However, three tools are essentially redundant aliases or near-duplicates (create_ask, get_responses, and possibly watch_ask given HTTP bridge equivalents), which could be consolidated. The count is not excessive or too thin, but the effective surface is smaller than 11 distinct tools.
The server covers creation (create_form, create_feedback_form), listing (list_asks, list_my_forms), reading responses (get_responses, get_my_form_responses), and real-time watching (watch_ask, watch_my_form_responses). However, there is no tool for updating or deleting existing forms, and no tool for closing/archiving a form. The creation-session tools are present but lack a corresponding read/view for drafts. The domain is form lifecycle, and update/delete operations for published forms are notable gaps.