unsubscribeCancel a subscription by id. Ownership is enforced — you can only cancel your own subscriptions. The row is deactivated (not deleted) so its historical events stay available via recent_alerts.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Subscription id (uuid) returned by subscribe. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses a critical behavioral trait not conveyed by the annotations: cancellation deactivates the row rather than deleting it, preserving historical events via recent_alerts. It also adds an ownership restriction, which is auth-related context. These details go well beyond the structured annotations, enriching the agent's understanding of side effects.
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 two sentences, tightly packed with essential information. The first sentence states the action and target; the second adds ownership and behavioral nuance. Every clause earns its place, with no filler or repetition of structured data.
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 single-parameter mutation tool with no output schema, the description covers everything an agent needs: what it does, the ownership constraint, the non-destructive deactivation behavior, and the implication for historical data availability. Combined with the idempotentHint and destructiveHint annotations, the context 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?
Schema description coverage is 100%, with the single parameter 'id' already documented as 'Subscription id (uuid) returned by subscribe.' The description's phrase 'Cancel a subscription by id' restates this without adding further semantic detail. Per the rubric, the baseline is 3 when the schema carries the full burden, which it does here.
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 opens with 'Cancel a subscription by id', a specific verb+resource construction that clearly identifies the tool's function. It goes further by adding ownership scope ('you can only cancel your own subscriptions'), which distinguishes it from generic cancellation tools and aligns with the sibling context of subscribe/list_subscriptions.
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 ownership enforcement statement provides clear context on when this tool can be used (only for subscriptions belonging to the caller). It does not explicitly name alternatives or state when-not-to-use, but the 'deactivated (not deleted)' clause implies it is the safe cancellation method when historical events must be preserved. The context is clear, though exclusions are not fully spelled out.
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.
The set mixes several overlapping clusters: three ask_pipeworx variants (beta is explicitly identical to stable right now), six Polymarket tools with similar opportunity-scanning purposes, and two AI-visibility tools that duplicate each other. However, the descriptions are detailed enough that an agent can usually pick correctly, so the ambiguity is moderate rather than severe.
Tool names follow no single convention — some are verb_noun (query_layer, validate_claim), some noun_noun (entity_profile, layer_info), some company-prefixed clusters (pipeworx_*, polymarket_*), and a few standalone verbs (forget, recall). While snake_case is consistent, the absence of a uniform verb_noun pattern across the set makes it unpredictable.
At 34 tools, the server is oversized for its apparent purpose, and the count is even more problematic because most tools belong to a general Pipeworx/data platform while only 3 serve the 'Arcgis Princewilliam' GIS theme. The set feels like two unrelated servers merged, with many tools earning no clear place in a unified product.
The GIS side is a read-only stub (search, schema, and query) with no editing or feature-level retrieval, and the broader Pipeworx side has a notable dead end: tools return pipeworx:// citation URIs but no tool is provided to fetch those resources. The result is a surface that is simultaneously over-built in prediction markets and under-built in its namesake domain.